© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-3-27B
53-GEMMASCOPE-2-RES-65K
1586
Prev
Next
MODEL
53-gemmascope-2-res-65k
Source/SAE
INDEX
Go
Explanations
bulgarian word fragments
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
Bulgarian language or culture
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
How To Load
Prompts (Dashboard)
392,802 prompts, 256 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-27b/53-gemmascope-2-res-65k/1586?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-27b/53-gemmascope-2-res-65k/1586?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
ڑھ
0.73
erhöhen
0.70
traiter
0.69
單
0.68
ﮐ
0.68
ziff
0.68
ﭘ
0.68
۴
0.66
೬
0.66
༧
0.66
POSITIVE LOGITS
съ
1.30
въ
1.18
въз
1.16
пър
1.16
повече
1.16
също
1.13
още
1.10
дъл
1.10
едно
1.09
из
1.09
Act
ivations
Density 0.004%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
