© 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. 17169
    Prev
    Next
    INDEX
    Explanations

    URLs with domain names

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

    website links and platforms

    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
    j
    0.61
    艾
    0.59
    G
    0.57
    d
    0.57
    柯
    0.57
    //!
    0.56
    m
    0.55
    HOL
    0.54
    胜
    0.53
    src
    0.52
    POSITIVE LOGITS
     can
    0.82
    in
    0.74
    ।
    0.72
    at
    0.71
     aérea
    0.68
    -
    0.67
     tuần
    0.66
     física
    0.65
    eron
    0.64
    ồng
    0.64
    Activations Density 0.004%

    No Known Activations