© 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. 10-GEMMASCOPE-RES-131K
    7. 47663
    Prev
    Next
    INDEX
    Explanations

    comma in dates

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

    This neuron detects document date stamps, specifically the month-day-year sequences in article headers.

    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
     you
    -1.87
     haberse
    -1.71
     понадоби
    -1.66
     disponer
    -1.62
     pouze
    -1.60
     presentarse
    -1.59
     hacerle
    -1.56
     hacerte
    -1.56
     baloncesto
    -1.52
     mantenerse
    -1.52
    POSITIVE LOGITS
     of
    1.95
    <bos>
    1.93
     those
    1.80
     more
    1.64
    はまだ
    1.48
    :”
    1.48
     ?”
    1.44
    理石
    1.43
     began
    1.42
     ZU
    1.39
    Activations Density 0.643%

    No Known Activations