© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8540
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on timestamp or date‐time markers (e.g. the “:” and surrounding numbers in “Last edited … at 01:23:45 PM”).

    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
     viš
    0.63
     promedio
    0.61
     Vial
    0.61
     stereotypes
    0.61
    𝐚
    0.61
     recomendado
    0.59
     comenzamos
    0.59
     maître
    0.58
    ட்டுகள்
    0.58
     buka
    0.58
    POSITIVE LOGITS
    상이
    0.63
    '.$
    0.62
    գ
    0.62
    𒌨
    0.62
     .'
    0.59
    п
    0.57
    문
    0.57
    我是
    0.56
    RY
    0.55
    ))))
    0.54
    Activations Density 0.000%

    No Known Activations