© 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. 71559
    Prev
    Next
    INDEX
    Explanations

    multilingual code and text

    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
    d
    -2.42
    ’
    -2.14
    -
    -1.88
     первого
    -1.84
     других
    -1.83
    姿势
    -1.83
    取る
    -1.80
     інших
    -1.73
     he
    -1.73
    ным
    -1.69
    POSITIVE LOGITS
     you
    2.23
    鶺
    2.23
     gatto
    2.06
     farmaco
    2.03
     vostre
    2.02
     Traducción
    1.91
     ieri
    1.88
    
    1.85
     vostra
    1.84
     pulsa
    1.84
    Activations Density 0.001%

    No Known Activations