© 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. 181918
    Prev
    Next
    INDEX
    Explanations

    boot at, Rufus software, leased land

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

    varying, directly, avoiding

    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
    ikalische
    0.49
    阿
    0.47
     Einzel
    0.44
    বার্গ
    0.44
    市镇
    0.44
    bür
    0.42
    ＋
    0.42
     بي
    0.42
    了我
    0.42
    באנגלית
    0.41
    POSITIVE LOGITS
     també
    0.50
     Guam
    0.50
     भिन्न
    0.48
     thus
    0.45
     chiefly
    0.45
    れば
    0.45
     aussi
    0.45
    uld
    0.44
     Samoa
    0.43
     derfor
    0.43
    Activations Density 0.000%

    No Known Activations