© 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. 7767
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on semicolon punctuation, effectively detecting the “;” list- or clause-separator.

    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
    लखनऊ
    0.84
    u
    0.82
    ΙΚ
    0.76
    爲
    0.74
     motivation
    0.73
     rebut
    0.72
    进口
    0.72
    局部
    0.71
    зва
    0.70
    澜
    0.69
    POSITIVE LOGITS
    тся
    0.98
    ujos
    0.82
    스타그램
    0.82
    ンド
    0.81
    angleOf
    0.80
    트롤
    0.79
     ইমর
    0.77
     тебя
    0.77
     acesso
    0.76
    너지
    0.75
    Activations Density 0.000%

    No Known Activations