© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93469
    Prev
    Next
    INDEX
    Explanations

    Christmas and holidays

    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
     Christmas
    -1.48
    Christmas
    -1.26
     christmas
    -1.23
     Halloween
    -1.22
     Valentine
    -1.16
     Thanksgiving
    -1.15
     Weihnachts
    -1.10
     valentine
    -1.09
     Valentines
    -1.05
    Halloween
    -1.01
    POSITIVE LOGITS
    presented
    0.79
     Bans
    0.76
    dedores
    0.75
     Peas
    0.73
    timore
    0.72
    𝓂
    0.71
     člán
    0.70
     HONORABLE
    0.69
    Wishlist
    0.68
    printer
    0.68
    Activations Density 0.023%

    No Known Activations