© 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 · 92570 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
92570

INDEX

Explanations

attribute/tag names

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

 having

-0.91

قاد

-0.85

so

-0.84

ਦੀ

-0.82

//<

-0.82

алы

-0.82

ibili

-0.79

aimerais

-0.77

 essentially

-0.76

 CreateTagHelper

-0.76

POSITIVE LOGITS

 PROFES

1.00

▦

0.90

ALLAS

0.90

 monst

0.90

wre

0.90

ATH

0.88

 folgendes

0.88

lity

0.88

 bottes

0.85

licious

0.84

Activations Density 0.006%

No Known Activations