© 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. 84776
    Prev
    Next
    INDEX
    Explanations

    people's names and associated works

    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
    '
    -3.16
    </i>
    -3.09
    it
    -2.91
     باسلام
    -2.83
     fährt
    -2.78
    We
    -2.75
    $
    -2.73
     With
    -2.67
    {
    -2.66
     This
    -2.64
    POSITIVE LOGITS
    尨
    3.17
    0
    2.95
    
    2.88
    ㍉
    2.86
     nimmer
    2.77
    ༀ
    2.61
    亖
    2.56
     devem
    2.53
    秕
    2.48
    ᥬ
    2.44
    Activations Density 0.011%

    No Known Activations