© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    This neuron detects proper names and brand‐ or product-style named entities (i.e. capitalized names, trademarks, locations, and other named entities).

    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
    -"
    0.90
    -',
    0.89
    :"",
    0.76
    -'
    0.74
    :'',
    0.72
    -(
    0.71
    -
    0.68
    -\\
    0.67
    ------
    0.66
    
    0.66
    POSITIVE LOGITS
     |”
    0.94
     &
    0.94
     @_
    0.92
     |
    0.91
     &.
    0.79
    ＆
    0.79
    ®
    0.78
     亀
    0.75
    ฯ
    0.75
    ‌پ
    0.72
    Activations Density 0.646%

    No Known Activations