© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135113
    Prev
    Next
    INDEX
    Explanations

    the following word

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive categories

    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
    6
    0.52
     población
    0.49
     Ці
    0.48
    殭
    0.46
     transcribe
    0.44
     redundant
    0.43
    ację
    0.43
     Comedy
    0.43
     fécond
    0.42
    راك
    0.41
    POSITIVE LOGITS
    اداس
    0.51
    fyd
    0.51
    pid
    0.49
    uede
    0.48
    );"
    0.48
    _);
    0.46
    QSizePolicy
    0.45
     ময়
    0.45
    mero
    0.45
    helby
    0.45
    Activations Density 0.001%

    No Known Activations