© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    birthday and celebrations

    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
     Weihnachts
    -0.95
    クリスマス
    -0.91
     Christmas
    -0.90
     CHRISTMAS
    -0.88
    Christmas
    -0.86
    yttö
    -0.79
     новогод
    -0.77
     christmas
    -0.77
     marriages
    -0.75
    圣诞
    -0.74
    POSITIVE LOGITS
     birthday
    3.52
    🎂
    2.73
     Birthday
    2.73
    Birthday
    2.59
    birthday
    2.56
     cake
    2.52
     birthdays
    2.09
     BIRTHDAY
    2.00
    生日
    1.91
     Geburtstag
    1.89
    Activations Density 0.032%

    No Known Activations