© 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. 69997
    Prev
    Next
    INDEX
    Explanations

    ℠ ® designation industry laser - ideal

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

    describing physical states

    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
     فایل
    0.52
     دائو
    0.50
    conscious
    0.49
    ﺤ
    0.49
    해보
    0.48
    Adobe
    0.47
    విత
    0.47
    ოფ
    0.46
    自由に
    0.46
    ქვთ
    0.46
    POSITIVE LOGITS
     h
    0.57
     can
    0.57
     in
    0.55
     dem
    0.53
     Centre
    0.52
     pregnant
    0.49
     mellitus
    0.49
     mis
    0.49
     Compliance
    0.49
     gas
    0.49
    Activations Density 0.001%

    No Known Activations