© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    time frequencies (daily, weekly, hourly)

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

    The neuron activates on expressions of recurring time intervals (e.g. hourly, daily, weekly, monthly, quarterly).

    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
     মহ
    0.70
    MediaPlayer
    0.69
     дзяржа
    0.69
     visor
    0.68
    $("
    0.68
     медицинской
    0.68
     '/':
    0.66
    "{
    0.64
     beatae
    0.63
     ವ
    0.62
    POSITIVE LOGITS
    ße
    0.76
    嘛
    0.70
    でしたが
    0.69
    甚至
    0.69
    ệu
    0.68
    では
    0.68
    粽
    0.67
    หรือ
    0.66
     tất
    0.66
    所有的
    0.66
    Activations Density 0.000%

    No Known Activations