© 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 · 74842 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
74842

INDEX

Explanations

Moi, HttpContext, Padre, imho, 比如, WOW

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

-2.52

ть

-2.42

 Immediately

-2.41

 Resultat

-2.31

はとても

-2.30

 δύο

-2.27

大声

-2.27

稣

-2.25

 Directly

-2.25

liam

-2.25

POSITIVE LOGITS

ቍ

2.64

er

2.59

镦

2.55

 hurtig

2.52

퐼

2.48

𓋼

2.48

to

2.47

 måde

2.44

猡

2.38

ſſel

2.19

Activations Density 0.001%

No Known Activations