© 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. 206059
    Prev
    Next
    INDEX
    Explanations

    countries, cities, and titles

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

    greentext style writing

    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
    class
    0.55
    ä
    0.48
    s
    0.48
     class
    0.48
     price
    0.46
     cigarette
    0.46
    cigarettes
    0.44
    Class
    0.44
     radically
    0.44
    4
    0.43
    POSITIVE LOGITS
    錡
    0.59
    ☦
    0.55
     अधिकारी
    0.51
     सरकार
    0.50
     ചെയ്യുന്നു
    0.49
     verwacht
    0.49
     devrait
    0.48
     Développement
    0.48
     σύμφωνα
    0.48
     ควร
    0.48
    Activations Density 0.002%

    No Known Activations