© 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. 85506
    Prev
    Next
    INDEX
    Explanations

    system calls and functions

    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
    쩡
    -1.50
    与此
    -1.48
     EUROPE
    -1.39
    óval
    -1.36
    այի
    -1.35
     могла
    -1.34
     ребёнка
    -1.34
     UIFont
    -1.33
    🚜
    -1.33
    彧
    -1.32
    POSITIVE LOGITS
     his
    2.20
    4
    1.88
     the
    1.79
    5
    1.76
    3
    1.67
    我就
    1.66
     ۶
    1.62
    7
    1.56
     alcune
    1.55
     ۳
    1.54
    Activations Density 0.005%

    No Known Activations