© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29175
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actéristi
    -3.09
    ſu
    -3.00
    鵙
    -2.95
    
    -2.84
    秶
    -2.77
    蓠
    -2.77
    沵
    -2.70
    纛
    -2.69
    䛗
    -2.56
    ཿ
    -2.55
    POSITIVE LOGITS
     if
    2.77
    ↵↵
    2.66
     in
    2.50
    ....
    2.45
     Since
    2.31
     before
    2.28
     when
    2.23
     after
    2.22
     at
    2.20
     Some
    2.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.