© 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-262K · 10738 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-262K
10738

INDEX

Explanations

structured data labels

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_262k_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

ب

1.47

 gerçekleştir

1.31

ంబేద్కర్

1.25

EntryPoint

1.24

Tens

1.22

lässlich

1.19

rsp

1.18

 sécur

1.15

ם

1.15

ysse

1.14

POSITIVE LOGITS

𝑒

1.33

ᴏ

1.31

 ओलंप

1.28

ᴀ

1.20

 unpleasant

1.18

𝑎

1.17

 Charitable

1.16

 nada

1.16

𝑔

1.15

ം

1.15

Activations Density 0.000%

No Known Activations