© 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. 217902
    Prev
    Next
    INDEX
    Explanations

    grating patches

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

    national champions

    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
    Y
    0.57
     Vien
    0.50
    ano
    0.47
     Munich
    0.46
    uszko
    0.46
    ivore
    0.46
     Saheb
    0.46
     Dar
    0.43
     Cab
    0.43
    yers
    0.43
    POSITIVE LOGITS
     فِي
    0.52
     nghề
    0.51
     請
    0.51
    Ｋ
    0.49
     مواقع
    0.49
    劍
    0.49
     來
    0.48
     watu
    0.48
     đạt
    0.47
    PEL
    0.47
    Activations Density 0.000%

    No Known Activations