© 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. 4561
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on person names (especially Chinese-style character names) in narrative 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
    呟
    1.02
     минуту
    1.00
     চিৎকার
    0.97
     comenzamos
    0.97
    лянчук
    0.97
     MDLVertex
    0.93
    beatCounter
    0.93
     divertida
    0.91
    讒
    0.91
    reactant
    0.90
    POSITIVE LOGITS
     -
    1.02
     historically
    1.01
     values
    0.95
     cases
    0.94
     such
    0.93
     historical
    0.91
     based
    0.89
     modern
    0.89
     data
    0.88
     historic
    0.88
    Activations Density 0.007%

    No Known Activations