© 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. 31555
    Prev
    Next
    INDEX
    Explanations

    dates including months and days

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

    The neuron activates on numeric date tokens—especially day‐of‐month numbers (with or without ordinal endings) in dates and schedules.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     lower
    -0.84
     sā
    -0.76
     varying
    -0.75
    组
    -0.75
    ียบ
    -0.73
    ární
    -0.72
    extra
    -0.71
    Exponent
    -0.71
    参考にして
    -0.71
    eak
    -0.70
    POSITIVE LOGITS
    צי
    0.93
    寄生
    0.79
     trimestre
    0.79
     julk
    0.76
    pona
    0.76
    ancang
    0.74
    πε
    0.73
     Rè
    0.73
    юр
    0.73
     of
    0.73
    Activations Density 0.038%

    No Known Activations