© 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-2-27B
10-GEMMASCOPE-RES-131K
113016
Prev
Next
MODEL
10-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
cloud services and infrastructure
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
references to cloud computing services or platforms.
oai_token-act-pair · claude-4-5-sonnet
Triggered by @bfgcn7frf5
No Scores
The main thing this neuron does is detect occurrences of the word “cloud,” as in references to cloud computing or cloud-based services.
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-27b-pt-res/layer_10/width_131k
Prompts (Dashboard)
24,576 prompts, 128 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-2-27b/10-gemmascope-res-131k/113016?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-2-27b/10-gemmascope-res-131k/113016?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
WRENCE
-2.00
zusätzlichen
-1.99
皷
-1.96
ますが
-1.93
上げる
-1.91
𨭆
-1.90
pouze
-1.76
Antes
-1.75
Eindruck
-1.74
躋
-1.73
POSITIVE LOGITS
]
2.86
{
2.28
)
2.28
雰
2.27
鍇
2.03
ihr
1.90
柽
1.87
色の
1.83
ي
1.81
珝
1.80
Act
ivations
Density 0.019%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations