© 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. 155031
    Prev
    Next
    INDEX
    Explanations

    office and administrative details

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

    office, files, and documents

    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
    ཎ
    0.58
     ежедневно
    0.53
     Pesach
    0.48
    㛲
    0.47
     чтобы
    0.46
     Пе
    0.46
     Մ
    0.46
    🏟
    0.46
     செல்சிய
    0.46
    工地
    0.46
    POSITIVE LOGITS
    is
    0.58
    office
    0.57
     office
    0.54
    INTEGER
    0.47
    isFile
    0.47
     administrative
    0.47
    bearers
    0.46
    文件
    0.44
    a
    0.44
    institutional
    0.43
    Activations Density 0.023%

    No Known Activations