© 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 · 22-GEMMASCOPE-2-RES-16K · 96 ｜ Neuronpedia

Home
Gemma-3-4B-IT
22-GEMMASCOPE-2-RES-16K
96

INDEX

Explanations

structured data comparisons

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_22_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

0.65

«

0.62

0.61

 what

0.60

0.60

 ..."

0.60

「

0.60

0.59

you

0.59

 chain

0.59

POSITIVE LOGITS



0.92

larghezza

0.89

 berlangsung

0.89

 mieszkańców

0.88

 preocupaciones

0.87

 wedstrijd

0.87



0.87

Thankfully

0.86

 ética

0.85

údio

0.83

Activations Density 0.209%

No Known Activations