© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7400
    Prev
    Next
    INDEX
    Explanations

    24/7 available

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

    This neuron flags temporal expressions—mentions of durations (e.g. “for days or weeks at a time”) and specific times of day or routines (e.g. “mostly nocturnal… sleeps throughout the day,” “in the morning… collapse on the sofa”).

    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
     하지만
    0.82
     אך
    0.80
     backstage
    0.74
     pero
    0.72
     wreath
    0.71
     But
    0.71
    但在
    0.71
     ولكن
    0.70
     received
    0.70
     nowadays
    0.70
    POSITIVE LOGITS
    殺人
    0.82
     EVERYTHING
    0.79
     terrified
    0.76
    とその
    0.75
    無論
    0.73
     wszystko
    0.73
    を行い
    0.72
    あらゆる
    0.71
    破壊
    0.71
    を開始
    0.70
    Activations Density 0.136%

    No Known Activations