© 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. 116437
    Prev
    Next
    INDEX
    Explanations

    non-english country names

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

    foreign languages and geography

    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
    Dealer
    0.47
    Movie
    0.46
    出
    0.46
     settings
    0.46
      
    0.45
    Settings
    0.45
    Farmer
    0.44
    Cert
    0.44
    नीत
    0.43
     Dealer
    0.43
    POSITIVE LOGITS
     Узбеки
    0.62
     យើង
    0.54
     Америка
    0.52
    ру
    0.51
     SOUTH
    0.50
     цей
    0.49
    та
    0.49
    ৮
    0.48
     INDI
    0.48
    ತ್ಮ
    0.47
    Activations Density 0.001%

    No Known Activations