© 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. 99107
    Prev
    Next
    INDEX
    Explanations

    programming constructs 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
    
    -1.74
    罍
    -1.66
     have
    -1.65
     and
    -1.56
    鬟
    -1.53
     energía
    -1.52
    踌
    -1.45
    
    -1.45
    髫
    -1.44
    宝贝
    -1.42
    POSITIVE LOGITS
     of
    2.16
     但是
    1.78
     But
    1.62
     that
    1.61
     However
    1.61
    来
    1.55
    !
    1.54
     但
    1.52
     Люди
    1.52
     Moreover
    1.49
    Activations Density 0.002%

    No Known Activations