© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1851
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is recognize numeric expressions (numbers, dates, times, counts, and related quantifiers).

    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
     misled
    0.87
     dehuman
    0.87
     聞い
    0.85
     GX
    0.84
    
    0.84
     disdain
    0.83
    <unused48>
    0.82
     hastily
    0.82
     fórmulas
    0.81
    녠
    0.80
    POSITIVE LOGITS
    ि
    0.82
    ִ
    0.70
    India
    0.68
     不是
    0.68
     તે
    0.67
    Beach
    0.67
    し
    0.67
    {"
    0.66
    ılan
    0.66
    Will
    0.66
    Activations Density 0.001%

    No Known Activations