© 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 · 17-GEMMASCOPE-2-RES-16K · 11081 ｜ Neuronpedia

Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-16K
11081

INDEX

Explanations

Budi Santoso

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

†

0.89

 Elliott

0.86

 collectible

0.83

 begann

0.82

formed

0.82

❦

0.82

 invol

0.82

Elliott

0.81

 PayPal

0.80

听

0.80

POSITIVE LOGITS

dengan

1.12

 đã

1.12

khi

1.09

ogyakarta

1.07

 đều

1.06

 trên

1.05

 của

1.04

và

1.03

 như

1.02

 yang

1.01

Activations Density 0.003%

No Known Activations