© 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. 188344
    Prev
    Next
    INDEX
    Explanations

    shy of

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

    action and progress

    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
    冰箱
    0.50
    ጲ
    0.49
    િક્
    0.49
    电影
    0.47
    ικ
    0.46
    इंडियन
    0.46
    <0xA4>
    0.46
    婶
    0.46
    وب
    0.45
    нти
    0.45
    POSITIVE LOGITS
     lead
    0.51
     führen
    0.51
     accounted
    0.49
     zcela
    0.48
    heben
    0.46
     söyl
    0.46
    reiben
    0.45
     lograr
    0.45
     shrugged
    0.44
     practiced
    0.43
    Activations Density 0.000%

    No Known Activations