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
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-27B-IT
40-GEMMASCOPE-2-RES-262K
14762
Prev
Next
MODEL
40-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
introducing an example
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-it/resid_post/layer_40_width_262k_l0_medium
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
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-it/40-gemmascope-2-res-262k/14762?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-it/40-gemmascope-2-res-262k/14762?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
ದ
0.38
できる
0.38
できる
0.37
出来る
0.37
वैसे
0.36
AKA
0.35
是可以
0.34
winkel
0.34
쾨
0.34
いくつ
0.34
POSITIVE LOGITS
say
2.17
假设
2.03
假設
1.96
suppose
1.93
Suppose
1.88
say
1.88
Suppose
1.74
assume
1.68
Say
1.66
Assume
1.66
Act
ivations
Density 0.066%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
