© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89763
    Prev
    Next
    INDEX
    Explanations

    code-golf and programming constructs

    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_34/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
     federal
    -0.80
     strong
    -0.78
     within
    -0.76
    waltung
    -0.73
     sł
    -0.73
    boli
    -0.73
     political
    -0.73
    IconModule
    -0.73
    xymatrix
    -0.72
    notifyListeners
    -0.69
    POSITIVE LOGITS
     golfing
    1.29
     golf
    1.25
    quine
    1.13
    golf
    1.07
     Golf
    1.05
     GOLF
    0.99
    Golf
    0.99
     PPC
    0.98
     PGA
    0.98
     golfers
    0.95
    Activations Density 0.054%

    No Known Activations