© 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. 99373
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     their
    -1.98
     create
    -1.65
     '
    -1.56
     can
    -1.50
     then
    -1.47
     through
    -1.47
     using
    -1.46
     provide
    -1.45
     because
    -1.44
     like
    -1.43
    POSITIVE LOGITS
    婠
    1.58
    
    1.55
     whimsical
    1.50
    蛲
    1.48
    艄
    1.45
    低调
    1.43
    鹇
    1.43
    Improve
    1.43
    錾
    1.42
    对他
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.