© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    This neuron detects capitalized named entities, such as manufacturer names and place names.

    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
    鲢
    0.82
    ዻ
    0.80
    uyến
    0.79
     montón
    0.79
     biç
    0.79
     birkaç
    0.79
    üssel
    0.79
    ούν
    0.78
     cultivos
    0.77
     geliş
    0.77
    POSITIVE LOGITS
    {
    0.65
     Rangers
    0.65
     יש
    0.64
     ਕਿ
    0.64
     신청
    0.63
    Ext
    0.62
     अस
    0.61
     Fact
    0.61
    mek
    0.61
    {//
    0.61
    Activations Density 0.000%

    No Known Activations