© 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. 22-GEMMASCOPE-RES-131K
    7. 15090
    Prev
    Next
    INDEX
    Explanations

    dates, deadlines, and timeframes

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

    The neuron fires on explicit date or time mentions (especially the word “date” and associated numeric schedule references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     reprez
    -1.15
     nivelul
    -1.06
    athies
    -1.05
    étranger
    -1.04
     scris
    -1.03
    _
    -1.02
    ながら
    -0.99
     multe
    -0.98
    うちの
    -0.98
     وصلة
    -0.98
    POSITIVE LOGITS
     date
    2.20
     dates
    1.63
     for
    1.45
    date
    1.32
    dates
    1.30
     schedule
    1.29
     deadline
    1.27
     deadlines
    1.26
     calendar
    1.21
    日期
    1.20
    Activations Density 0.024%

    No Known Activations