© 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. 7713
    Prev
    Next
    INDEX
    Explanations

    The neuron responds whenever it encounters numeric tokens (quantities, figures, dates, percentages, page numbers, etc.).

    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
     Такой
    1.03
    Veja
    0.96
     Такие
    0.95
     Каждый
    0.90
    anakk
    0.89
     станет
    0.89
    ف
    0.89
     Кстати
    0.88
    ńskiej
    0.88
     Sudah
    0.88
    POSITIVE LOGITS
    :
    0.79
    ,
    0.75
     classification
    0.74
     destruction
    0.72
     incorrectly
    0.69
     insufficient
    0.69
     reflectors
    0.68
     various
    0.68
                        
    0.66
     parameters
    0.66
    Activations Density 0.001%

    No Known Activations