© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    percentages, numbers, or counts

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

    The neuron strongly responds to numeric tokens that denote time intervals or durations (e.g. minutes or seconds).

    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
    swering
    0.58
    િજા
    0.56
     বিষয়ক
    0.55
    构
    0.54
    ⿸
    0.54
     situation
    0.54
     Other
    0.54
    ジュアル
    0.54
    ructuring
    0.52
    c
    0.52
    POSITIVE LOGITS
    しかし
    0.63
    吃
    0.61
     až
    0.59
    ıklı
    0.59
    Virat
    0.58
     maksimal
    0.58
    ƴ
    0.57
    最多
    0.57
     voire
    0.57
     максимум
    0.57
    Activations Density 0.054%

    No Known Activations