© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    false, in, trust, valuable

    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
     单
    0.76
     указыва
    0.71
    ::__
    0.69
     поез
    0.69
    쿰
    0.69
    已被
    0.68
     таких
    0.68
     באמצעות
    0.67
     egent
    0.66
    TreeClassifier
    0.66
    POSITIVE LOGITS
     immortality
    0.84
    વ
    0.82
     Univers
    0.77
     pharmacological
    0.77
     premise
    0.77
    았다
    0.77
    այ
    0.76
    ла
    0.75
    𝘂
    0.73
     Pharmac
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.