© 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. 61362
    Prev
    Next
    INDEX
    Explanations

    symbolic and structured text

    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
    ாதார
    0.42
     นิด
    0.40
    ِل
    0.38
    порт
    0.37
    caria
    0.37
    依照
    0.37
    념
    0.36
     virtu
    0.36
    யி
    0.36
    tahun
    0.36
    POSITIVE LOGITS
    Glasgow
    0.41
    numbered
    0.37
     букмекеры
    0.37
     GGA
    0.37
    ೆಯಲ್ಲಿ
    0.36
     nuggets
    0.36
     ներ
    0.36
    行
    0.36
     কোম্প
    0.36
     crunchy
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.