© 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 · 34-GEMMASCOPE-RES-131K · 45390 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
45390

INDEX

Explanations

my account

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_34/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

私たち

-0.78

 Nuit

-0.76

 TextInputType

-0.76

getUsers

-0.75

éroport

-0.74

tegen

-0.74

országban

-0.73

 ян

-0.73

 UIFont

-0.73

ights

-0.72

POSITIVE LOGITS

My

2.86

My

2.66

my

2.48

MY

2.02

 profile

1.99

my

1.98

 account

1.97

 我的

1.95

profile

1.76

getMy

1.76

Activations Density 0.070%

No Known Activations