© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51033
    Prev
    Next
    INDEX
    Explanations

    technical specific terms

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

    update device settings

    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
     geralmente
    0.50
    ಾ
    0.48
     xuất
    0.47
     genellikle
    0.47
     macer
    0.46
    breadcrumb
    0.46
     customPlot
    0.46
     প্রথমে
    0.46
     informations
    0.46
     выполнения
    0.45
    POSITIVE LOGITS
    贺
    0.54
     देखना
    0.46
    澤
    0.46
    .^
    0.44
     Jh
    0.44
    Package
    0.42
    <!
    0.42
    ietro
    0.41
     Vishnu
    0.41
    $('#
    0.41
    Activations Density 0.000%

    No Known Activations