© 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. 174043
    Prev
    Next
    INDEX
    Explanations

    Baja Mexico regions

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

    Mexico locations

    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
     käs
    0.44
    墂
    0.44
     perspekt
    0.41
    Mexican
    0.40
    瓄
    0.39
     ViewData
    0.39
     perspectives
    0.39
    بع
    0.38
     Mexican
    0.38
    μέ
    0.38
    POSITIVE LOGITS
     पंजाब
    0.45
     Tob
    0.42
    sequelize
    0.38
    chent
    0.38
     forg
    0.38
     glandular
    0.37
     girder
    0.37
     '');
    0.37
    slategray
    0.37
     Concord
    0.37
    Activations Density 0.020%

    No Known Activations