© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32618
    Prev
    Next
    INDEX
    Explanations

    begins and dates

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

    The main thing this neuron does is detect temporal expressions—specifically words and numbers indicating dates, days, times, or the start of events.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    During
    -1.09
     then
    -1.09
     podczas
    -1.01
    ájá
    -1.00
     that
    -0.96
     During
    -0.95
     ბ
    -0.95
     during
    -0.95
     both
    -0.91
     related
    -0.91
    POSITIVE LOGITS
     시작
    1.91
    เริ่ม
    1.87
     start
    1.87
    開始
    1.67
     commencer
    1.65
     starts
    1.64
     commences
    1.61
     beginning
    1.58
     начать
    1.58
     begins
    1.57
    Activations Density 0.053%

    No Known Activations