© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 255991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ances
    0.47
     открыть
    0.46
     увеличить
    0.46
    鐒
    0.46
    ൺലൈ
    0.45
     भागा
    0.45
     తగ్గ
    0.44
    另外
    0.44
    jectory
    0.44
     చేయడానికి
    0.44
    POSITIVE LOGITS
     :
    0.50
     Blueberry
    0.49
    :
    0.49
     Simplified
    0.44
     MMP
    0.44
     Audi
    0.43
     -
    0.43
     Estudio
    0.43
     Impro
    0.43
     Ac
    0.42
    Activations Density 0.001%

    No Known Activations