© 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. 85206
    Prev
    Next
    INDEX
    Explanations

    describing surfaces or properties

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

    not interrupting

    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
    Negative Logits
    tä
    0.50
    package
    0.48
     Karna
    0.48
    profen
    0.47
    icu
    0.46
    ት
    0.45
    elem
    0.45
    icier
    0.45
    trivia
    0.45
    elae
    0.44
    POSITIVE LOGITS
     μέχρι
    0.57
     nouvel
    0.53
     시작
    0.52
     удержи
    0.52
    箐
    0.50
     ਕ
    0.49
     بدء
    0.49
     جديد
    0.48
     направлении
    0.48
     алгорит
    0.48
    Activations Density 0.000%

    No Known Activations