© 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. 34376
    Prev
    Next
    INDEX
    Explanations

    Mexico

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

    Mexico and Mexican cuisine

    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
     Belarusian
    0.52
    樺
    0.51
     Rhode
    0.50
    ńcz
    0.48
     Bangladeshi
    0.48
     Tasmanian
    0.47
    纽
    0.47
    瓯
    0.46
     Christchurch
    0.44
     Ulster
    0.44
    POSITIVE LOGITS
     Mexico
    2.00
     Mexican
    1.98
    Mexico
    1.98
     Мекси
    1.95
    Mexican
    1.95
     Mexicans
    1.91
     México
    1.89
    墨西哥
    1.88
    México
    1.82
     mexico
    1.80
    Activations Density 0.096%

    No Known Activations