© 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. 39577
    Prev
    Next
    INDEX
    Explanations

    East Asia and related countries

    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
     impecable
    -1.76
    gencias
    -1.64
    Biografia
    -1.64
    €“
    -1.57
     یکی
    -1.57
     posible
    -1.57
    もし
    -1.56
    ゚
    -1.56
     första
    -1.55
    När
    -1.55
    POSITIVE LOGITS
     on
    2.33
     by
    2.06
     similar
    1.95
     even
    1.88
     more
    1.87
     to
    1.83
     also
    1.81
     then
    1.81
     On
    1.71
     especially
    1.71
    Activations Density 0.048%

    No Known Activations