© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1289
    Prev
    Next
    INDEX
    Explanations

    time of day schedules

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

    The neuron strongly activates on tokens that mark event times (hour numbers and “am”/“pm” markers) in schedules.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ن
    0.64
     callus
    0.53
     septum
    0.52
     technologically
    0.50
    న్ని
    0.50
     versatile
    0.50
    那就是
    0.50
    더라도
    0.50
    x
    0.50
     dias
    0.49
    POSITIVE LOGITS
    晚餐
    0.93
     बजे
    0.89
    dinner
    0.78
     brunch
    0.77
    🌇
    0.76
     akşam
    0.74
     Dinner
    0.73
     Brunch
    0.72
    lunch
    0.72
    起床
    0.72
    Activations Density 0.110%

    No Known Activations