© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7067
    Prev
    Next
    INDEX
    Explanations

    units of time

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

    This neuron detects numeric time-interval expressions (e.g., a number combined with units like days, hours, years).

    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_31_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
     পর্যন্ত
    0.61
     trước
    0.57
     μέχρι
    0.57
     долго
    0.57
     অবধি
    0.57
    yearly
    0.57
    年に
    0.55
     hasta
    0.54
     перед
    0.54
    Until
    0.54
    POSITIVE LOGITS
     time
    0.89
    时间
    0.76
    从
    0.75
     tijd
    0.74
    的时间
    0.73
     kể
    0.70
    时间内
    0.70
    從
    0.69
     thereafter
    0.68
     aika
    0.67
    Activations Density 0.187%

    No Known Activations