© 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. 13082
    Prev
    Next
    INDEX
    Explanations

    The neuron is a “noun detector” that lights up on content‐bearing nouns (especially plural or entity labels) in the 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
     возраста
    0.77
     Константи
    0.75
     Reifen
    0.73
     Это
    0.72
    ской
    0.71
    ဋ
    0.70
     гиб
    0.69
    ︵
    0.68
     establecer
    0.68
     interchangeably
    0.67
    POSITIVE LOGITS
    ee
    0.71
    mation
    0.71
    ড়া
    0.70
     січня
    0.70
     involunt
    0.70
     portato
    0.70
    namento
    0.68
     custodians
    0.68
    rades
    0.67
     QSOs
    0.66
    Activations Density 0.000%

    No Known Activations