© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5224
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on occurrences of executive or leadership titles (e.g., Founder, CEO, President, Vice President).

    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
    zovaniyu
    0.75
     oamenii
    0.71
    <unused2116>
    0.69
     закончи
    0.68
     শিক্ষক
    0.66
     intitul
    0.66
    Одна
    0.66
     samod
    0.66
     преподава
    0.64
    くらいの
    0.64
    POSITIVE LOGITS
     and
    0.96
     &
    0.93
     và
    0.73
     και
    0.71
    er
    0.68
     (
    0.67
     एवं
    0.67
    and
    0.66
     و
    0.66
     of
    0.65
    Activations Density 0.013%

    No Known Activations