© 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. 102797
    Prev
    Next
    INDEX
    Explanations

    RUBY gems and configuration

    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
     module
    -0.79
     đông
    -0.79
     Plin
    -0.75
    ⌇
    -0.74
     Handic
    -0.72
     inclusion
    -0.68
     makro
    -0.68
     Clarinet
    -0.67
    iennes
    -0.67
     modules
    -0.67
    POSITIVE LOGITS
     gem
    0.89
    쇠
    0.87
    Push
    0.78
     PURPOSE
    0.78
     escritos
    0.77
    雷霆
    0.75
     gems
    0.73
     Harris
    0.73
     (~
    0.71
     Ще
    0.71
    Activations Density 0.107%

    No Known Activations