© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44592
    Prev
    Next
    INDEX
    Explanations

    country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     but
    -1.98
     that
    -1.73
     všetky
    -1.70
     Semua
    -1.52
    yoruz
    -1.50
     všetkých
    -1.48
    他們
    -1.44
     Semoga
    -1.43
    ناك
    -1.42
     and
    -1.41
    POSITIVE LOGITS
    了几
    1.52
    出了一
    1.46
     några
    1.40
     nele
    1.34
     comanda
    1.34
    ٪
    1.31
     asisten
    1.31
     terá
    1.29
     evangé
    1.29
    了不少
    1.28
    Activations Density 0.082%

    No Known Activations