ModelGemma 3 27B IT
Gemma-3-27B-IT
An instruction-tuned large language model from Google's Gemma 3 series with 27 billion parameters, designed for text understanding and generation tasks.
Timeline (last 90 days)
Oct 9
On the Gemma-3-27B-IT probe model, probes targeting high-risk and harmful responses require only approximately 80 samples to approach the performance plateau.
Unverified50%