© 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. 71497
    Prev
    Next
    INDEX
    Explanations

    people by nationality

    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
     a
    -1.66
     different
    -1.56
     the
    -1.47
    と言って
    -1.35
     varying
    -1.35
     various
    -1.33
     różnych
    -1.30
     związane
    -1.28
     including
    -1.27
     diversos
    -1.27
    POSITIVE LOGITS
    เรา
    1.45
     parfüm
    1.40
    vlád
    1.40
     policía
    1.35
     parfü
    1.33
     restoran
    1.30
    itize
    1.27
    ཫ
    1.27
    Ћ
    1.26
     двух
    1.24
    Activations Density 0.102%

    No Known Activations