© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30674
    Prev
    Next
    INDEX
    Explanations

    links to pdfs and websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thermo
    0.43
     Tuscany
    0.42
     와
    0.40
     federal
    0.40
     litter
    0.40
     Regno
    0.40
     Premio
    0.39
     garages
    0.39
     ಡಿ
    0.39
    SQLALCHEMY
    0.39
    POSITIVE LOGITS
    Dowell
    0.42
    حدة
    0.40
    👆
    0.40
    сү
    0.40
    multiple
    0.39
     يق
    0.39
     nextPage
    0.39
    неопр
    0.39
    notch
    0.38
    lesssim
    0.37
    Activations Density 0.000%

    No Known Activations