© 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. 240082
    Prev
    Next
    INDEX
    Explanations

    run ofdevotion tostrong businessmovie craftedslopes ofShe met

    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
    Ao
    0.53
    ^{-
    0.47
    =<
    0.47
    tak
    0.47
    多次
    0.47
    geq
    0.46
    Ae
    0.46
     aufgenommen
    0.46
    Apparently
    0.46
    Jennifer
    0.45
    POSITIVE LOGITS
     ડ
    0.46
     Кон
    0.45
     библиоте
    0.43
     Classified
    0.43
     использу
    0.43
     હત્યા
    0.43
     કાર
    0.42
     ਜ
    0.41
    ند
    0.40
    諡
    0.40
    Activations Density 0.000%

    No Known Activations