© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5906
    Prev
    Next
    INDEX
    Explanations

    This neuron detects named entities—proper names of people, publications, and similar capitalized designations.

    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_31_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
    UEFA
    0.67
     UEFA
    0.61
    队长
    0.56
     unsaturated
    0.55
     equivariant
    0.55
     immunity
    0.54
     सूत्रों
    0.53
    🏐
    0.52
     reformation
    0.52
     dizziness
    0.51
    POSITIVE LOGITS
     Writers
    2.31
     literary
    2.28
     novelists
    2.27
     Literary
    2.22
     escritores
    2.22
     novelist
    2.19
     writers
    2.11
     Writer
    2.09
     литератур
    2.00
     писатель
    1.99
    Activations Density 1.147%

    No Known Activations