© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119893
    Prev
    Next
    INDEX
    Explanations

    our followed by noun

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

    AI detection

    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
    Negative Logits
    ﾇ
    0.50
    культур
    0.49
    文化
    0.47
    禊
    0.47
    iers
    0.47
    もん
    0.46
    ере
    0.46
     культур
    0.44
    юр
    0.44
    剧
    0.43
    POSITIVE LOGITS
     maravill
    0.52
    [-\
    0.48
    {-\
    0.47
    Fcm
    0.46
     Admit
    0.45
    negl
    0.45
    Tarjeta
    0.45
    wellery
    0.44
     দায়িত্বে
    0.44
    jeeling
    0.43
    Activations Density 0.000%

    No Known Activations