© 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. 96505
    Prev
    Next
    INDEX
    Explanations

    contained asbestos

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

    methods, reports, and dates

    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
    悝
    0.54
    𝟎
    0.53
    闶
    0.52
    ᱐
    0.48
     Володи
    0.47
     活动
    0.47
     Espagne
    0.47
    ഷ്ണ
    0.47
    ȏ
    0.47
    淒
    0.46
    POSITIVE LOGITS
    area
    0.55
     and
    0.54
    ,
    0.54
     reflux
    0.53
    diet
    0.52
    menu
    0.50
     slic
    0.49
    date
    0.46
     Reg
    0.46
    sib
    0.45
    Activations Density 0.003%

    No Known Activations