© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-4B-IT · 17-GEMMASCOPE-2-RES-16K · 16222 ｜ Neuronpedia

Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-16K
16222

INDEX

Explanations

#include <header>

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

呟

1.31

Discard

1.25

Cyan

1.24

手动

1.19

Fluent

1.16

ąda

1.15

GameObject

1.14

 eget

1.12

锥

1.11

Callback

1.10

POSITIVE LOGITS

आगे

1.27

 niet

1.22

 intricate

1.19

 lifegu

1.18

 wildlife

1.18

 inclination

1.17

 incorporating

1.14

 delving

1.12

 occasional

1.11

 lurking

1.11

Activations Density 0.023%

No Known Activations