© 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. 193758
    Prev
    Next
    INDEX
    Explanations

    locations and associated services

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

    shade adorns, facing material, keep in

    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
    頊
    0.48
     東
    0.46
    Linux
    0.46
    瓄
    0.45
     gadgets
    0.44
     upgrad
    0.43
    omes
    0.43
    ud
    0.42
    I
    0.42
    sete
    0.42
    POSITIVE LOGITS
    临床
    0.43
    两侧
    0.43
     محبوب
    0.42
     alcune
    0.42
    ارو
    0.42
    肩膀
    0.42
    VIC
    0.41
    外科
    0.41
     unbek
    0.41
     dott
    0.41
    Activations Density 0.000%

    No Known Activations