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
5701
Prev
Next
MODEL
40-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
concepts followed by definitions
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
titles/headings and salient domain-specific terms or proper nouns that signal the main topic of a passage.
oai_token-act-pair · gpt-5
Triggered by @yooniel31
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/5701?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/5701?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
ਪ
0.14
यामुळे
0.14
ل
0.14
גם
0.13
פ
0.13
ഭ
0.13
etc
0.13
ल
0.12
ਕੋ
0.12
alte
0.12
POSITIVE LOGITS
®,
0.19
:
0.17
と呼ばれる
0.16
®
0.15
™,
0.15
®.
0.14
Vs
0.13
ؓ
0.13
(
0.13
—
0.13
Act
ivations
Density 2.726%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
