© 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-3-4B-IT · 29-GEMMASCOPE-2-RES-65K · 2269 ｜ Neuronpedia

Home
Gemma-3-4B-IT
29-GEMMASCOPE-2-RES-65K
2269

INDEX

Explanations

HOME to Crisis Text Line

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_29_width_65k_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

mortar

0.67

 charge

0.62

ก

0.62

estris

0.61

Charge

0.61

 talks

0.60

 Charge

0.60

늄

0.58

instance

0.58

 instance

0.58

POSITIVE LOGITS

 دی

0.66

㳒

0.63

 glTexParameteri

0.63

延

0.62

ຝ

0.62

 واحد

0.62

Buf

0.61

 дослід

0.60

㓈

0.60

చ్చే

0.58

Activations Density 0.139%

No Known Activations