© 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. 130267
    Prev
    Next
    INDEX
    Explanations

    "Q:" questions, names, dates, times

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

    The neuron detects scheduling details—dates, times, and related numeric information for announced events or services.

    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
    ệu
    -1.78
     mengumumkan
    -1.77
     THESE
    -1.70
     innumer
    -1.66
     anunció
    -1.66
     controladores
    -1.65
     ofrece
    -1.62
     diferentes
    -1.59
     diversos
    -1.59
    这些
    -1.56
    POSITIVE LOGITS
     and
    2.25
     with
    1.99
     at
    1.95
     one
    1.78
     an
    1.70
     more
    1.67
     before
    1.51
     after
    1.50
     but
    1.50
     K
    1.50
    Activations Density 0.004%

    No Known Activations