© 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. 85642
    Prev
    Next
    INDEX
    Explanations

    world revolves

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

    application maintenance

    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
     форм
    0.56
     ermöglicht
    0.55
    Ꭷ
    0.55
     найбільш
    0.52
    ೫
    0.50
     세계
    0.50
     מלא
    0.50
     ಸಾಕಷ್ಟು
    0.48
     மிகவும்
    0.48
    ༞
    0.48
    POSITIVE LOGITS
     campa
    0.47
     Maha
    0.45
     ousted
    0.45
     condoms
    0.40
    Qa
    0.40
    ционе
    0.39
     Lu
    0.39
    Lu
    0.39
     Kamp
    0.39
     Makh
    0.39
    Activations Density 0.000%

    No Known Activations