© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23631
    Prev
    Next
    INDEX
    Explanations

    month and its separators

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

    The neuron activates on date/time format specifiers and related regex tokens (e.g. “%Y‐%m‐%d”, “dd/mm/yyyy”, etc.).

    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
    YEAR
    -1.18
     YEAR
    -1.16
     año
    -0.96
    year
    -0.93
     year
    -0.93
    Year
    -0.90
     سنة
    -0.83
    Mink
    -0.82
     years
    -0.82
     год
    -0.79
    POSITIVE LOGITS
     month
    1.56
    getMonth
    1.27
     months
    1.27
     Month
    1.26
    Month
    1.16
    month
    1.08
    меся
    0.94
     mesi
    0.88
    Months
    0.78
     Months
    0.78
    Activations Density 0.018%

    No Known Activations