© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-3-27B
40-GEMMASCOPE-2-RES-16K
9807
Prev
Next
MODEL
40-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
Julia or Yu names
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
uint, Julia, Yu, uuid, youtube
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_40_width_16k_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/40-gemmascope-2-res-16k/9807?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/40-gemmascope-2-res-16k/9807?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
výrob
0.47
verdi
0.38
剌
0.38
ls
0.37
niger
0.37
Пло
0.36
શી
0.36
হল
0.36
vlá
0.36
धू
0.36
POSITIVE LOGITS
Julia
0.52
Julia
0.52
유
0.50
varlak
0.49
यु
0.46
यू
0.46
ユ
0.45
Yu
0.44
যু
0.43
ยุ
0.42
Act
ivations
Density 0.124%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
