© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-4B-IT · 17-GEMMASCOPE-2-RES-16K · 631 ｜ Neuronpedia

Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-16K
631

INDEX

Explanations

to verb

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-it/resid_post/layer_17_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

в

0.71

त

0.63

 umož

0.63

್

0.57

сно

0.55

р

0.55

ש

0.54

 momenta

0.54

 wana

0.52

0.52

POSITIVE LOGITS

ivals

0.58

ities

0.56

WITH

0.55

 instincts

0.54

 relies

0.54

 ‘‘

0.53

 ontological

0.51

 applauded

0.51

➢

0.51

cms

0.51

Activations Density 0.376%

No Known Activations