© 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
8970
Prev
Next
MODEL
40-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
Hol followed by ga or gas
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
Hol sound sequence
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
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/8970?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/8970?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
算是
0.42
OVE
0.39
reciate
0.38
iedo
0.38
이
0.38
지난
0.37
κάπο
0.37
रखकर
0.36
䨐
0.36
ही
0.36
POSITIVE LOGITS
Hol
0.80
Hol
0.80
hol
0.73
HOL
0.62
holo
0.57
Holistic
0.57
홀
0.54
hol
0.50
holog
0.50
holl
0.50
Act
ivations
Density 0.101%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
