© 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. 21152
    Prev
    Next
    INDEX
    Explanations

    symbols and equations

    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
    providedIn
    -1.78
    inemann
    -1.68
    んびり
    -1.65
    了一個
    -1.64
     freaking
    -1.64
     blissful
    -1.64
     this
    -1.59
     mammoth
    -1.55
    鴛
    -1.55
     zelen
    -1.54
    POSITIVE LOGITS
     juf
    1.84
    '
    1.80
    );
    1.79
     are
    1.73
     drey
    1.63
    ）、
    1.63
     gela
    1.62
    后
    1.62
     disposto
    1.60
    赑
    1.60
    Activations Density 0.001%

    No Known Activations