© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13339
    Prev
    Next
    INDEX
    Explanations

    timestamps

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

    The neuron detects numeric date‐ and time‐stamp patterns (e.g. “2016-06-08 10:13:16”).

    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
    пикир
    0.61
     Middles
    0.57
    ویان
    0.57
    煖
    0.57
    RxDocument
    0.57
     قاعدة
    0.55
     Nemours
    0.55
    برد
    0.54
     کردم
    0.54
    पृथ्वी
    0.54
    POSITIVE LOGITS
    T
    0.70
     günü
    0.61
     বিকালে
    0.56
    0
    0.55
    Ｔ
    0.55
    日
    0.54
     বিকেলে
    0.53
    午
    0.52
     ۱۵
    0.52
    ZT
    0.51
    Activations Density 0.090%

    No Known Activations