© 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. 221374
    Prev
    Next
    INDEX
    Explanations

    publishing circle

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

    in short, i'm designed

    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
     fórmulas
    0.49
    ীয়
    0.46
     مصرى
    0.45
     çizg
    0.45
     bảy
    0.42
    قية
    0.42
     ponctué
    0.42
    <unused2027>
    0.42
     बचेगा
    0.41
    ပြန်
    0.40
    POSITIVE LOGITS
    ke
    0.58
    timber
    0.49
    klik
    0.49
     ठिका
    0.49
    kom
    0.48
     bull
    0.47
    vem
    0.47
    eban
    0.47
    所在地
    0.47
     ਹੋ
    0.46
    Activations Density 0.003%

    No Known Activations