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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7899
    Prev
    Next
    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    
    -2.17
     Grup
    -1.81
    趿
    -1.77
    
    -1.75
     rangs
    -1.74
     maji
    -1.70
    ਗ਼
    -1.70
    蟊
    -1.70
     teo
    -1.70
     sain
    -1.69
    POSITIVE LOGITS
     at
    2.23
     in
    2.20
     also
    2.09
     Since
    1.95
    Also
    1.93
    There
    1.91
     However
    1.91
     from
    1.88
     on
    1.84
     time
    1.84
    Activations Density 0.039%

    No Known Activations