© 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 · 99799 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
99799

INDEX

Explanations

chances are

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

▰

-1.37

選んだ

-1.33

 shenan

-1.33

⸫

-1.29

 devoid

-1.29

imetsu

-1.27

就没

-1.27

 ſont

-1.25

TypeService

-1.25

baikan

-1.24

POSITIVE LOGITS

 that

1.97

,”

1.80

突然

1.43

kket

1.42

</h4>

1.42

tividade

1.39

During

1.38

」(

1.38

 Händen

1.34

ximadamente

1.32

Activations Density 0.037%

No Known Activations