© 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. 217883
    Prev
    Next
    INDEX
    Explanations

    foreign or english phrases

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

    lists of words or phrases

    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
     entscheid
    0.47
    tte
    0.46
    ínio
    0.46
    tted
    0.46
     !”
    0.45
    ifiés
    0.44
     »
    0.44
    ıl
    0.44
     pizarra
    0.43
    otherArchive
    0.43
    POSITIVE LOGITS
    EXCLUSIVE
    0.54
     مجھے
    0.53
    Camera
    0.52
    Exclusive
    0.49
    Beta
    0.48
    Kya
    0.48
    Dress
    0.47
    YG
    0.47
     Закон
    0.47
    Trung
    0.47
    Activations Density 0.001%

    No Known Activations