© 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. 73934
    Prev
    Next
    INDEX
    Explanations

    LMS sync, transfers, track, robots, only

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

    descriptive continuations

    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
    ם
    0.62
     rosto
    0.56
     maneiras
    0.54
    ן
    0.53
    ֹ
    0.50
    隂
    0.50
     днів
    0.50
    ัท
    0.49
    гідно
    0.49
    嫵
    0.48
    POSITIVE LOGITS
    $
    0.49
     Clubhouse
    0.44
    Tools
    0.44
    getLevel
    0.43
    loc
    0.42
    idic
    0.42
     Nickelodeon
    0.41
     Tools
    0.41
    会出现
    0.41
    <0xA7>
    0.41
    Activations Density 0.001%

    No Known Activations