© 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. 185074
    Prev
    Next
    INDEX
    Explanations

    Katalog fauny Polski

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

    Date Palms, Application, Ancient technology, pattern recognition

    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
    这样一个
    0.47
    逓
    0.45
     gepubliceerd
    0.44
     promulgating
    0.43
     Colonial
    0.43
     உதவும்
    0.43
     Державний
    0.43
     შედ
    0.42
     spada
    0.42
     инсу
    0.41
    POSITIVE LOGITS
    日
    0.56
    SELL
    0.55
    اول
    0.54
    Sell
    0.52
    вто
    0.50
    Rak
    0.49
    าว
    0.49
    ло
    0.48
    面
    0.47
    ه
    0.47
    Activations Density 0.000%

    No Known Activations