© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

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

GEMMA-3-27B · 53-GEMMASCOPE-2-RES-65K · 7578 ｜ Neuronpedia

Home
Gemma-3-27B
53-GEMMASCOPE-2-RES-65K
7578

INDEX

Explanations

dates and numbers

np_acts-logits-general · gemini-2.5-flash-lite

file path or folder path

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

രിൽ

0.32

URNIZ

0.29

 gelegen

0.29

瑚

0.29

⎦

0.28

ర్కొ

0.28

 NPTypeCode

0.28

桝

0.27

◸

0.27

 പൊതു

0.27

POSITIVE LOGITS

0.38

0.33

0.31

<0xC2>

0.29

//

0.29

var

0.29

0.29

</strong>

0.28

</

0.28

user

0.28

Activations Density 0.000%

No Known Activations