© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 68528 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
68528

INDEX

Explanations

what comes next

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

Negative Logits

釓

-2.38

ydi

-2.33

῞

-2.31

}$

-2.30

ErrUnexpectedEOF

-2.28

𐍆

-2.27

なもの

-2.25

吊

-2.25

AddTagHelper

-2.19

恸

-2.16

POSITIVE LOGITS

↵

3.66

In

3.00

 Previously

2.78

2.63

他

2.41

 ‘’

2.39

2.36

 mientras

2.34

2.28

 Importantly

2.27

Activations Density 0.010%

No Known Activations