© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    nationalities or geographic indicators

    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
     maravilloso
    -1.86
     "
    -1.75
    <bos>
    -1.70
    GEBUR
    -1.68
     cuarent
    -1.66
    の魅力
    -1.63
     plumas
    -1.61
     desperdic
    -1.59
     komplex
    -1.59
    íte
    -1.57
    POSITIVE LOGITS
    },
    1.88
     và
    1.68
     of
    1.63
     getGroup
    1.61
     getCount
    1.59
    na
    1.59
     parseFrom
    1.59
     حتى
    1.58
     및
    1.56
     監督
    1.55
    Activations Density 0.042%

    No Known Activations