© 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. 34-GEMMASCOPE-RES-131K
    7. 63822
    Prev
    Next
    INDEX
    Explanations

    Russian and Eastern European 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_34/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
    Tú
    -0.81
     esti
    -0.77
    Nhap
    -0.77
    Tá
    -0.75
    Result
    -0.73
     idx
    -0.71
    Guarda
    -0.70
    кза
    -0.69
     Seems
    -0.68
    спорти
    -0.68
    POSITIVE LOGITS
    strum
    0.94
     Marlins
    0.93
     doctrina
    0.91
    п
    0.90
     Witte
    0.88
     torebka
    0.88
    愠
    0.88
     IOS
    0.86
    IOS
    0.84
     třeba
    0.82
    Activations Density 0.020%

    No Known Activations