© 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. 110051
    Prev
    Next
    INDEX
    Explanations

    Hubbard OR High School

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

    list separators or structured content

    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
    ية
    0.47
    cji
    0.44
     اي
    0.42
    مكن
    0.42
    ➔
    0.41
    靂
    0.41
    ys
    0.41
    ور
    0.41
     यूज्ड
    0.41
    atically
    0.40
    POSITIVE LOGITS
    ショルダー
    0.55
    hb
    0.49
    typography
    0.44
     হাব
    0.43
     Desenvolvimento
    0.42
     accesorios
    0.42
    theater
    0.41
     निशाना
    0.41
    ීම්
    0.41
     curb
    0.41
    Activations Density 0.000%

    No Known Activations