© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15671
    Prev
    Next
    INDEX
    Explanations

    December and Christmas dates

    np_acts-logits-general · gemini-2.5-flash-lite

    December dates and Christmas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aug
    0.66
     April
    0.59
     봄
    0.57
    April
    0.55
     APRIL
    0.55
     June
    0.54
    Aug
    0.54
    봄
    0.54
     Summer
    0.53
    april
    0.52
    POSITIVE LOGITS
     Christmas
    2.19
    Christmas
    2.13
     क्रिसमस
    2.13
    🎄
    2.00
    圣诞
    1.99
     christmas
    1.97
    christmas
    1.97
     Xmas
    1.97
    クリスマス
    1.95
    December
    1.92
    Activations Density 0.349%

    No Known Activations