© 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. 795
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to detect the filler/list-continuation token “etc.” whenever it appears.

    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
    ن
    0.73
    度和
    0.66
    م
    0.66
     හෝ
    0.63
    性和
    0.61
    ン
    0.61
    इसे
    0.60
     جنوب
    0.60
     και
    0.60
    または
    0.60
    POSITIVE LOGITS
    etera
    1.39
    등
    1.03
    etc
    0.94
    .,
    0.87
     usw
    0.84
     وغیرہ
    0.83
     etc
    0.82
    等等
    0.81
    .).
    0.80
     väldigt
    0.78
    Activations Density 0.028%

    No Known Activations