© 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. 84668
    Prev
    Next
    INDEX
    Explanations

    proper names and surnames

    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
    ."
    -2.17
     Some
    -1.98
     here
    -1.89
     那
    -1.89
     This
    -1.84
     That
    -1.82
     zarówno
    -1.82
     Hinblick
    -1.77
    !
    -1.76
     Those
    -1.75
    POSITIVE LOGITS
    
    1.73
    ut
    1.55
    she
    1.47
     概念
    1.44
    箧
    1.43
    AdvEx
    1.43
    تاريخ
    1.43
    
    1.42
    reduce
    1.42
    垕
    1.41
    Activations Density 0.093%

    No Known Activations