© 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. 21547
    Prev
    Next
    INDEX
    Explanations

    links to GitHub files

    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
     is
    -2.27
     and
    -1.72
     in
    -1.69
     ако
    -1.59
    october
    -1.46
     by
    -1.42
    truc
    -1.40
    品的
    -1.39
     By
    -1.39
     So
    -1.37
    POSITIVE LOGITS
     their
    2.13
    袛
    1.77
     inspiri
    1.66
    alers
    1.66
     each
    1.63
    Kelebihan
    1.62
     definición
    1.60
     mày
    1.53
    ,”
    1.50
    
    1.48
    Activations Density 0.006%

    No Known Activations