© 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. 61369
    Prev
    Next
    INDEX
    Explanations

    day/night/year before or after

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

    The main thing this neuron does is find words indicating time periods or temporal references (e.g., day, night, weekend, year).

    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
     ſy
    -1.82
    assertEqual
    -1.77
    ización
    -1.76
     engran
    -1.74
    횃
    -1.72
    ări
    -1.71
     provocado
    -1.70
    ’，
    -1.70
     ſte
    -1.68
    棪
    -1.68
    POSITIVE LOGITS
    ↵
    1.86
    あれば
    1.82
     you
    1.66
     aid
    1.62
    l
    1.61
    -
    1.56
    m
    1.56
     [
    1.53
     augen
    1.53
     when
    1.52
    Activations Density 0.017%

    No Known Activations