© 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. 149644
    Prev
    Next
    INDEX
    Explanations

    show, have, could, what, grandfather, Sequence

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

    API calls and linguistic elements

    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
    쎌
    0.48
    シェル
    0.46
    rolling
    0.45
    のだが
    0.45
    тельство
    0.43
    if
    0.43
    rjust
    0.43
    рас
    0.43
    ებულია
    0.42
    Вакансия
    0.42
    POSITIVE LOGITS
     .{
    0.50
     احتيا
    0.47
     .\
    0.46
    同样的
    0.46
     दै
    0.45
     zdję
    0.44
     içi
    0.44
     ဒီ
    0.44
     ব্যা
    0.43
     vậy
    0.43
    Activations Density 0.000%

    No Known Activations