© 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. 77936
    Prev
    Next
    INDEX
    Explanations

    VirtualBox, PDF ability

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

    languages and cultures

    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
     ใด
    0.46
    QUI
    0.45
    ELINE
    0.45
    UM
    0.44
     png
    0.44
    Я
    0.43
    PREFIX
    0.42
     rigging
    0.42
    ਵੇ
    0.42
    🗿
    0.41
    POSITIVE LOGITS
     Lutheran
    0.50
     Parcel
    0.47
     Luther
    0.47
     ухуд
    0.46
     Điều
    0.46
     Adjust
    0.45
     Stuart
    0.45
     Kathleen
    0.44
     Irvine
    0.44
     Obstet
    0.43
    Activations Density 0.007%

    No Known Activations