© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133390
    Prev
    Next
    INDEX
    Explanations

    country codes and separators

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

    country codes and names

    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
    富士
    0.43
     fútbol
    0.39
     fü
    0.38
    brewer
    0.38
     erop
    0.38
     tractor
    0.38
    oncé
    0.38
     松
    0.38
     flavored
    0.37
    ored
    0.37
    POSITIVE LOGITS
    Serbia
    0.50
     Serbia
    0.46
     ದೇಶ
    0.45
     Yugoslavia
    0.45
     Bosnia
    0.43
     Organisations
    0.43
     Generated
    0.43
     Germany
    0.42
     germany
    0.42
     Greece
    0.41
    Activations Density 0.017%

    No Known Activations