© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    alpha, battery, BBQ, dataclass

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     =
    0.55
     is
    0.54
    ty
    0.52
     fumar
    0.52
    ü
    0.49
    я
    0.49
    ia
    0.49
     of
    0.48
    ся
    0.48
    var
    0.48
    POSITIVE LOGITS
     έχουν
    0.53
     États
    0.48
     basaltes
    0.48
    ႅ
    0.48
     kwietnia
    0.47
    슌
    0.47
     जेसीबी
    0.47
     twierd
    0.47
     órdenes
    0.46
     entraîne
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.