© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 1261 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
1261

INDEX

Explanations

regular or irregular

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 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

-2.33

↵↵

-2.28



-2.25

-2.22

但

-2.16

 opulent

-2.13

 serán

-2.05

 célèbre

-2.03

 unveils

-2.03

 incred

-2.02

POSITIVE LOGITS

?”

2.75

”:

2.34

蛧

2.27

瑧

2.22

!”

2.19

ஂ

2.13

鷓

2.08

Even

2.06

 meticulously

2.06

哢

1.91

Activations Density 0.015%

No Known Activations