© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    steps in a sequence

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

    The neuron detects ordinal list markers – words like “first,” “second,” “third,” etc., that introduce sequential points or sections.

    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
     primeiros
    0.73
     Ausnahme
    0.72
     ۵
    0.68
     कई
    0.68
     первых
    0.68
     مِن
    0.67
     primeira
    0.66
     fives
    0.66
     кеңсеси
    0.65
     ஐந்து
    0.65
    POSITIVE LOGITS
    ，
    0.66
    主題
    0.65
    義
    0.65
    他又
    0.63
    activiti
    0.63
    。
    0.61
    Secondly
    0.61
    社会
    0.60
    മാണ്
    0.59
    、【
    0.59
    Activations Density 0.221%

    No Known Activations