© 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. 9501
    Prev
    Next
    INDEX
    Explanations

    acts and requests

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

    FROM :

    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
     開始
    0.42
    otene
    0.38
    ่าย
    0.37
    ವಾರು
    0.36
     qīng
    0.33
    স্য
    0.33
    $&$-
    0.32
     それ
    0.32
     これは
    0.32
     clockRadius
    0.32
    POSITIVE LOGITS
     Dato
    0.39
     Erk
    0.38
     an
    0.37
     Kota
    0.35
     Esquire
    0.35
     göre
    0.35
     Prakash
    0.34
     Industrie
    0.34
     ilg
    0.33
     the
    0.33
    Activations Density 0.002%

    No Known Activations