© 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. 65899
    Prev
    Next
    INDEX
    Explanations

    code formatting or 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
    Completed
    -0.79
     Utah
    -0.75
    μαστε
    -0.74
     Heaven
    -0.74
     قدرت
    -0.73
    folded
    -0.72
     Township
    -0.72
     Muslim
    -0.71
    
    -0.71
     cuad
    -0.70
    POSITIVE LOGITS
    Guerra
    0.80
     osmotic
    0.71
     Napoleonic
    0.68
     bulldog
    0.68
     hobo
    0.66
    iany
    0.66
     tricycle
    0.65
    锤
    0.65
     scrip
    0.65
     Gwend
    0.64
    Activations Density 0.046%

    No Known Activations