© 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. 232089
    Prev
    Next
    INDEX
    Explanations

    business development and features

    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
    에
    0.54
    ason
    0.48
    uit
    0.48
    amente
    0.46
    ون
    0.45
    に
    0.44
    aison
    0.43
    水
    0.43
    iné
    0.42
    oup
    0.42
    POSITIVE LOGITS
     xhrObj
    0.53
     róż
    0.51
    ﹟
    0.48
    <unused511>
    0.48
     bibliography
    0.47
     bitOp
    0.46
     pern
    0.46
     öğret
    0.46
     smothered
    0.46
    স্পতিবার
    0.45
    Activations Density 0.001%

    No Known Activations