© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106334
    Prev
    Next
    INDEX
    Explanations

    hot springs and spa

    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
    Negative Logits
    breakpoints
    -0.75
     freezer
    -0.75
    Workspace
    -0.73
     aldehyde
    -0.71
     knockdown
    -0.71
     ice
    -0.71
    لب
    -0.70
    主婦
    -0.70
     Sharp
    -0.70
    ternut
    -0.69
    POSITIVE LOGITS
     bath
    1.84
     baths
    1.78
     spa
    1.60
     thermal
    1.48
     bathing
    1.47
    ♨
    1.41
    Thermal
    1.35
     Baths
    1.35
     geothermal
    1.35
     Bath
    1.25
    Activations Density 0.019%

    No Known Activations