© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9417
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    此时
    0.79
    黛
    0.59
     instantiate
    0.56
    关键
    0.55
    データを
    0.55
    情報は
    0.54
    quela
    0.53
    зо
    0.52
     instead
    0.52
    初始化
    0.52
    POSITIVE LOGITS
     Universität
    0.71
     Serviços
    0.68
     Gelände
    0.68
    餬
    0.66
    érence
    0.65
     finde
    0.65
     მთ
    0.65
     blí
    0.65
     jó
    0.63
    <unused10>
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.