© 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. 119507
    Prev
    Next
    INDEX
    Explanations

    after periods or events

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

    This neuron activates on mentions of hours as time or duration (e.g. “after hours,” “opening hours,” numeric spans with “hours”).

    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
    魮
    -1.97
    </h1>
    -1.83
    おわりに
    -1.82
    がっ
    -1.80
    新た
    -1.80
    䉴
    -1.78
    𐑂
    -1.75
    えっ
    -1.73
    鐒
    -1.70
    癰
    -1.70
    POSITIVE LOGITS
     of
    2.02
    This
    1.97
    These
    1.90
     These
    1.86
    。”
    1.73
     '
    1.73
    0
    1.62
    海南
    1.60
    The
    1.58
    ViewChild
    1.58
    Activations Density 0.004%

    No Known Activations