© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-4B-IT · 9-GEMMASCOPE-2-RES-262K · 10262 ｜ Neuronpedia

Home
Gemma-3-4B-IT
9-GEMMASCOPE-2-RES-262K
10262

INDEX

Explanations

after text in phrases

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

 отрасли

1.26

 الاعزاء

1.15

NORE

1.14

<unused2019>

1.13

 Gericht

1.12

 প্রয়োজনে

1.11

 atvej

1.10

可以说

1.09

<unused2074>

1.09

렛

1.07

POSITIVE LOGITS

р

1.39

 dran

1.19

νου

1.13

bek

1.11

一身

1.08

sal

1.06

 sweet

1.04

 denominator

1.04

rn

1.03

maa

1.03

Activations Density 0.000%

No Known Activations