© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8950
    Prev
    Next
    INDEX
    Explanations

    nationalities and associated roles

    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
    ’
    -2.75
    ༷
    -2.55
     semelh
    -2.48
     begann
    -2.45
     escucha
    -2.42
     ........
    -2.34
    t
    -2.34
    ৄ
    -2.33
     irse
    -2.33
    ↵↵
    -2.31
    POSITIVE LOGITS
    idjan
    2.50
    */
    2.41
    vantaged
    2.27
    ？！
    2.23
    Only
    2.22
    ום
    2.20
    
    2.17
     スタッフ
    2.16
     were
    2.14
     店内
    2.14
    Activations Density 0.032%

    No Known Activations