© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229475
    Prev
    Next
    INDEX
    Explanations

    printable pictures

    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
    メニュー
    0.53
     chuan
    0.51
    人を
    0.48
     współpracy
    0.47
     ዘዴ
    0.46
     တစ်
    0.46
     began
    0.46
     宮
    0.45
    ဟု
    0.45
    zept
    0.45
    POSITIVE LOGITS
    comand
    0.50
     Motiv
    0.49
     Anim
    0.47
    樂
    0.47
     Animated
    0.46
     Offline
    0.46
    Drivers
    0.44
     Dealing
    0.44
     Drivers
    0.44
     Motivation
    0.43
    Activations Density 0.000%

    No Known Activations