© 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. 69134
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or conjunctions

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

    largest, common, or eliminates

    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
    爐
    0.48
    春秋
    0.47
    在
    0.46
    )->
    0.46
    两
    0.46
    蘭
    0.46
    Gov
    0.46
    狗
    0.46
    炉
    0.46
    ->__
    0.45
    POSITIVE LOGITS
    otherapeutic
    0.46
     чрез
    0.45
    powr
    0.44
     Ks
    0.44
    yty
    0.44
    cy
    0.43
    oys
    0.43
     Pendidikan
    0.43
     Fórmula
    0.43
     සහිත
    0.43
    Activations Density 0.000%

    No Known Activations