© 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. 128661
    Prev
    Next
    INDEX
    Explanations

    the country Japan

    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
    ’,
    -2.73
    ’.
    -2.69
    ?"
    -2.53
    
    -2.50
    苼
    -2.39
    ."
    -2.34
     Профиль
    -2.28
    ’:
    -2.22
    ).
    -2.17
    .”
    -2.16
    POSITIVE LOGITS
    b
    2.67
    e
    2.61
    1
    2.59
    -
    2.30
    人の
    2.20
    </b>
    2.17
    amur
    2.17
    Already
    2.14
     religions
    2.09
    Still
    2.06
    Activations Density 0.016%

    No Known Activations