© 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 · 9-GEMMASCOPE-2-RES-16K · 226 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-16K
226

INDEX

Explanations

transportation, rides, and travel

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_9_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

nya

1.04

у

1.01

 увагу

0.96

onium

0.91

tség

0.89

শালী

0.89

ו

0.89

 password

0.87

 العافيه

0.85

agma

0.84

POSITIVE LOGITS

💨

1.28

騨

1.24

سلام

1.14

驒

1.13

 locomotives

1.11

 ferries

1.08

സ

1.05

 Fahrt

1.05

ح

1.03

 Passengers

1.02

Activations Density 0.492%

No Known Activations