© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10123
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on proper nouns, especially names of people, places, countries, and 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_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
    特效
    0.74
     WPF
    0.73
    QUENCY
    0.73
    姆
    0.69
     McKay
    0.69
    啤酒
    0.68
    频谱
    0.68
    腾
    0.67
    马来
    0.67
     Btu
    0.66
    POSITIVE LOGITS
     Italian
    2.88
    Italian
    2.84
    イタリア
    2.80
     Italians
    2.70
     italien
    2.66
     italian
    2.64
     Italy
    2.63
     итальян
    2.63
     italiano
    2.61
    Italy
    2.59
    Activations Density 0.645%

    No Known Activations