© 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. 56082
    Prev
    Next
    INDEX
    Explanations

    available to

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

    available

    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
     in
    0.70
     في
    0.69
    جميع
    0.66
     الآن
    0.61
    ني
    0.60
    ۹
    0.59
    もあった
    0.58
     uitgevoerd
    0.57
     tất
    0.57
     جميع
    0.57
    POSITIVE LOGITS
    ur
    0.76
    де
    0.73
    to
    0.72
    ai
    0.71
    '
    0.71
    z
    0.71
    ا
    0.69
    f
    0.67
    as
    0.66
    (
    0.66
    Activations Density 0.032%

    No Known Activations