© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-3-4B-IT · 29-GEMMASCOPE-2-RES-65K · 2166 ｜ Neuronpedia

Home
Gemma-3-4B-IT
29-GEMMASCOPE-2-RES-65K
2166

INDEX

Explanations

romanian and spanish questions

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

 subpo

0.79

agon

0.75

 अंतर्गत

0.73

herent

0.72

 Debido

0.70

 தொடர்பாக

0.70

ității

0.67

 fornire

0.67

祂

0.66

Men

0.66

POSITIVE LOGITS

 cred

0.82

 credibility

0.81

tot

0.77

 Cred

0.73

 daca

0.71

cum

0.68

da

0.67

 multa

0.66

TOT

0.65

am

0.65

Activations Density 0.001%

No Known Activations