© 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. 83048
    Prev
    Next
    INDEX
    Explanations

    module and theme usage

    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
    Gol
    -0.78
     analyst
    -0.71
     опу
    -0.70
     Optionen
    -0.69
    AVG
    -0.67
    Davidson
    -0.66
    
    -0.66
    全集
    -0.66
     footballer
    -0.66
     heyday
    -0.66
    POSITIVE LOGITS
     module
    1.02
     theme
    1.01
    modules
    0.97
    Themes
    0.92
    模块
    0.89
    広島
    0.87
     themes
    0.87
    THEME
    0.86
     modules
    0.85
     MODULE
    0.84
    Activations Density 0.043%

    No Known Activations