© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on standalone, capitalized “heading-style” tokens (e.g. section titles or document header words) rather than ordinary text.

    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
    фа
    0.94
    мон
    0.89
    сла
    0.87
    а
    0.78
    סה
    0.77
    তার
    0.76
    ⅾ
    0.76
    дии
    0.75
     comparação
    0.75
    ɗ
    0.75
    POSITIVE LOGITS
     Band
    0.75
     ended
    0.70
    oing
    0.69
     gird
    0.68
     انته
    0.68
     cholesterol
    0.65
    毕
    0.65
     (
    0.64
    apag
    0.64
     lleno
    0.63
    Activations Density 0.014%

    No Known Activations