© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    acquisition, family, approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    Copy
    0.79
    In
    0.76
    work
    0.75
    ك
    0.75
    ruary
    0.71
    '!
    0.71
    Eo
    0.70
    Common
    0.69
    .!
    0.69
    ploy
    0.68
    POSITIVE LOGITS
     sebesar
    0.87
    ่ม
    0.82
     gruesome
    0.77
     รถ
    0.77
     wszystkie
    0.76
     negros
    0.76
     mutilated
    0.76
     ڕ
    0.75
     бясплат
    0.75
     cynical
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.