© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117518
    Prev
    Next
    INDEX
    Explanations

    christmas nativity

    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
     funerals
    -0.78
     funeral
    -0.77
    ModelAndView
    -0.74
     Mosquito
    -0.73
     pourraient
    -0.73
     mourners
    -0.73
     Viking
    -0.72
    Viking
    -0.71
    yttö
    -0.71
     Ulysses
    -0.70
    POSITIVE LOGITS
     Nativity
    1.95
     Bethlehem
    1.95
     nativity
    1.86
     manger
    1.69
     birth
    1.56
     shepherds
    1.50
     Christmas
    1.30
    ativity
    1.29
     Birth
    1.23
    Christmas
    1.20
    Activations Density 0.016%

    No Known Activations