© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15875
    Prev
    Next
    INDEX
    Explanations

    mechanical seal

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

    This neuron fires strongly on the first principal content word of a new sentence or segment (often a capitalized word immediately following a break).

    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_31_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
    三人
    0.86
    он
    0.80
    上述
    0.79
    ồng
    0.78
    クリック
    0.77
    寸
    0.75
    その他
    0.74
    大胆
    0.74
    柴
    0.73
    ằng
    0.72
    POSITIVE LOGITS
     supposition
    0.76
     subjecting
    0.69
     salle
    0.68
     suscit
    0.67
     sciences
    0.67
     gatherings
    0.67
     predictors
    0.66
     desirous
    0.66
     stopwords
    0.66
     unregulated
    0.66
    Activations Density 0.000%

    No Known Activations