© 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. 170399
    Prev
    Next
    INDEX
    Explanations

    descriptions of events

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

    concerns with, happened, might

    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
     Смо
    0.49
     Мари
    0.46
     ومن
    0.46
    㮆
    0.46
    ية
    0.45
     Кі
    0.45
    álie
    0.44
    ستی
    0.44
     Люди
    0.44
    ایہ
    0.43
    POSITIVE LOGITS
     obtained
    0.50
    $,
    0.48
     becomes
    0.47
     equilibrated
    0.46
    rightsquigarrow
    0.46
     placeholders
    0.45
     ở
    0.45
     $,
    0.45
    在
    0.45
     unambiguous
    0.44
    Activations Density 0.001%

    No Known Activations