© 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. 260169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    平台
    0.46
    ที่เรา
    0.45
    klasse
    0.44
    ไตล์
    0.44
    フォルダ
    0.43
    千万
    0.43
    及时
    0.42
    ＋
    0.41
    ファイルを
    0.41
    Math
    0.41
    POSITIVE LOGITS
    lap
    0.47
     اذ
    0.47
     ограни
    0.46
    νη
    0.46
     مف
    0.46
     ох
    0.46
     Ordin
    0.45
    叐
    0.44
     atractivo
    0.44
    avk
    0.43
    Activations Density 0.000%

    No Known Activations