© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 60543 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
60543

INDEX

Explanations

permanent, perma, permalloy, permalink

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

geſ

-2.11

⢅

-1.98

⸀

-1.91

ሖ

-1.88

 tenets

-1.88

㉔

-1.80

￬

-1.79

ཌ

-1.75

 antiguas

-1.73

大腿

-1.72

POSITIVE LOGITS

2.00

?”

1.98

</sup>

1.96

}$

1.93

”

1.88

许久

1.85

 Several

1.83

 After

1.80

 Regardless

1.80

 While

1.79

Activations Density 0.009%

No Known Activations