© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2065
    Prev
    Next
    INDEX
    Explanations

    months and monthly events

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

    The neuron detects date and time references (tokens that form calendar dates, e.g. month names, day and year numbers, punctuation like “:”).

    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
     month
    -1.13
     annually
    -1.01
     weeks
    -0.92
     annual
    -0.88
     ANNUAL
    -0.87
    année
    -0.86
    ummer
    -0.85
    woche
    -0.83
     annum
    -0.82
     week
    -0.80
    POSITIVE LOGITS
     monthly
    0.87
    份
    0.77
    crates
    0.73
    Featured
    0.73
     hiệu
    0.72
     featured
    0.71
     Satellite
    0.69
     menurut
    0.68
     Оль
    0.67
     Vernon
    0.66
    Activations Density 0.064%

    No Known Activations