© 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. 60154
    Prev
    Next
    INDEX
    Explanations

    cleaning and rebuilding

    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
     cleanliness
    -1.31
     washable
    -1.07
    Cleaning
    -0.99
     unclean
    -0.98
    Cleanup
    -0.96
     cleanup
    -0.95
    清洁
    -0.93
     cleanser
    -0.93
    CLEAN
    -0.92
     yaa
    -0.91
    POSITIVE LOGITS
     repair
    0.82
     remove
    0.79
     removing
    0.78
     putting
    0.76
    ージ
    0.71
     гор
    0.70
    AMAHA
    0.69
     prepare
    0.68
     protection
    0.68
     reducing
    0.68
    Activations Density 0.033%

    No Known Activations