© 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. 13259
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on tokens that are (parts of) people’s proper 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_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
      
    0.34
     fantast
    0.31
    ↵↵
    0.30
    ↵
    0.30
     DUI
    0.30
     DDoS
    0.30
     elektro
    0.29
     Midwest
    0.29
     TV
    0.28
     Chicago
    0.28
    POSITIVE LOGITS
    ِي
    0.32
    爯
    0.32
    irà
    0.31
    觟
    0.31
    εν
    0.31
    upar
    0.31
    ã
    0.31
    ﻜ
    0.31
    ън
    0.30
     राव
    0.30
    Activations Density 0.156%

    No Known Activations