© 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. 10-GEMMASCOPE-RES-131K
    7. 45245
    Prev
    Next
    INDEX
    Explanations

    New Year's Eve, Christmas Day

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

    The neuron flags tokens that mark calendar dates or date-related terms (e.g. numeric day values like “24” and words like “Eve”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     wichtigsten
    -1.70
     podendo
    -1.67
     Después
    -1.66
    ”،
    -1.63
     Pueden
    -1.63
     Mientras
    -1.59
     所以
    -1.58
     Algunas
    -1.57
    擽
    -1.55
     Debido
    -1.52
    POSITIVE LOGITS
     and
    1.75
    📡
    1.59
     also
    1.59
    肜
    1.55
    ia
    1.50
    “……”
    1.42
     or
    1.41
     piernas
    1.39
    ists
    1.38
    owanie
    1.38
    Activations Density 0.015%

    No Known Activations