© 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. 113264
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with integrals and logarithms

    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
    cnico
    -1.79
     Mainly
    -1.78
    XmlAccessorType
    -1.73
     Achieving
    -1.70
    
    -1.69
     Exciting
    -1.69
    
    -1.69
    牂
    -1.65
     Dealing
    -1.63
    berfläche
    -1.63
    POSITIVE LOGITS
     from
    2.02
     without
    1.97
    ↵
    1.88
     while
    1.84
     with
    1.80
     you
    1.79
     it
    1.79
    >
    1.73
     one
    1.70
     for
    1.66
    Activations Density 0.011%

    No Known Activations