© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8287
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on named entities—proper nouns, dates, numbers, and other tokens that mark specific people, places, events, or organizations.

    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
    .
    0.82
    ,.
    0.76
    ,
    0.72
     would
    0.66
    .,
    0.64
    Flair
    0.63
    Duties
    0.62
     امور
    0.61
    Webster
    0.61
     already
    0.60
    POSITIVE LOGITS
     jaundice
    0.79
     provoque
    0.69
     prevenir
    0.68
    因
    0.68
     tsunami
    0.67
    忘记
    0.66
     empêcher
    0.65
     kvůli
    0.65
    两次
    0.64
     стимули
    0.64
    Activations Density 0.069%

    No Known Activations