© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 40-GEMMASCOPE-2-RES-16K · 9630 ｜ Neuronpedia

Home
Gemma-3-27B-IT
40-GEMMASCOPE-2-RES-16K
9630

INDEX

Explanations

negative conjunctions or negations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ன்படி

0.40

 more

0.40

而不是

0.40

itsar

0.39

而非

0.38

やすく

0.38

 সিনেম

0.38

 बोलो

0.38

 onge

0.38

 tyle

0.37

POSITIVE LOGITS

nor

1.57

nor

1.38

也没有

1.29

也沒有

1.26

Nor

1.19

Nor

1.13

 tampoco

1.04

也不会

0.89

NOR

0.89

也不能

0.88

Activations Density 0.378%

No Known Activations