© 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. 67459
    Prev
    Next
    INDEX
    Explanations

    other and mutual relationships

    np_acts-logits-general · gemini-2.5-flash-lite

    programming special characters and extensions

    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
     ۔
    0.59
    ن
    0.49
    ک
    0.49
    ۔
    0.48
     Section
    0.47
     Invasion
    0.46
     Stamp
    0.46
    ं
    0.46
     Haziran
    0.46
    ோ
    0.46
    POSITIVE LOGITS
    の効果
    0.49
     microbiological
    0.48
    嗶
    0.47
     triphosphate
    0.46
     অন্যদের
    0.46
    geoType
    0.46
     অন্যরা
    0.45
    ურთიერთ
    0.44
    体験
    0.43
     riguard
    0.43
    Activations Density 0.002%

    No Known Activations