© 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. 85665
    Prev
    Next
    INDEX
    Explanations

    local and geographical terms

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

    foreign languages and 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
    Negative Logits
    ር
    0.39
    Giovanni
    0.39
    ੀ
    0.39
    нинг
    0.38
    Xem
    0.37
    Hlav
    0.37
    rubyg
    0.37
    ни
    0.36
    世界上
    0.36
    վ
    0.36
    POSITIVE LOGITS
     local
    0.95
     locally
    0.93
     우리나라
    0.89
    local
    0.84
     Locally
    0.84
     한국
    0.83
     বাংলাদেশে
    0.80
     местные
    0.80
    本地
    0.79
     мест
    0.78
    Activations Density 0.688%

    No Known Activations