© 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. 222118
    Prev
    Next
    INDEX
    Explanations

    links, services, and endorsements

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

    car history family ultrasonic sensor

    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
    is
    0.67
    en
    0.62
    on
    0.62
    il
    0.58
    at
    0.54
    un
    0.54
    o
    0.54
    az
    0.53
    EN
    0.53
     bane
    0.52
    POSITIVE LOGITS
    ႁ
    0.59
    hā
    0.50
     déten
    0.48
     Dung
    0.48
     accum
    0.48
    લો
    0.47
    цій
    0.47
     apprezz
    0.47
     UHF
    0.46
     Manch
    0.46
    Activations Density 0.000%

    No Known Activations