© 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. 4011
    Prev
    Next
    INDEX
    Explanations

    boundary, demarcation, lines, direction

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

    The neuron strongly activates on tokens that appear at the beginnings of lines or list items, effectively marking where a new section or bullet starts.

    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
     просмо
    0.69
    \{
    0.68
     apiece
    0.64
     $\{(
    0.64
     each
    0.62
    <>
    0.62
     টাকা
    0.61
    =\$
    0.61
     राजधानी
    0.60
     けど
    0.59
    POSITIVE LOGITS
     sustancias
    0.73
     পদার্থ
    0.73
    eynman
    0.70
     mitologia
    0.69
     स्वातंत्र्य
    0.67
     adsorbent
    0.67
    ylidene
    0.66
     പു
    0.65
    tiger
    0.65
    皇帝
    0.64
    Activations Density 0.000%

    No Known Activations