© 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. 10-GEMMASCOPE-RES-131K
    4. 11390
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    The neuron is specialized in spotting numerical tokens—especially times, dates, and other quantitative figures—in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     or
    -3.28
     that
    -2.56
     such
    -2.11
     where
    -2.08
     their
    -2.05
     when
    -2.05
     which
    -1.98
     as
    -1.91
     what
    -1.88
     When
    -1.79
    POSITIVE LOGITS
     فقط
    1.89
    𓆏
    1.52
     BETWEEN
    1.52
     diinginkan
    1.50
     is
    1.49
    IBLIO
    1.46
     Portugu
    1.45
     zaragoza
    1.45
     accepte
    1.45
     alho
    1.43
    Activations Density 0.074%

    No Known Activations