© 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. 225977
    Prev
    Next
    INDEX
    Explanations

    educational films, copyrights reserved

    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
     limited
    0.41
    HEAT
    0.41
     Declar
    0.40
    AQ
    0.40
     nuestra
    0.39
    has
    0.39
     elég
    0.38
    -
    0.38
     competence
    0.38
     conferring
    0.38
    POSITIVE LOGITS
    🏈
    0.47
     procé
    0.46
    ੧
    0.45
    操作系统
    0.43
    დი
    0.42
     Sist
    0.42
     ಪ್ರಕಾರ
    0.41
    เสมอ
    0.40
     영화
    0.40
     ਉਸ
    0.39
    Activations Density 0.000%

    No Known Activations