© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3489
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric expressions (quantities, measurements, percentages, and other numbers) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Those
    1.11
    Those
    1.09
     those
    1.00
     那
    0.98
     THAT
    0.94
    those
    0.94
     eso
    0.89
    那是
    0.88
     That
    0.87
    That
    0.86
    POSITIVE LOGITS
    这款
    1.47
     acest
    1.44
     هذا
    1.39
    this
    1.38
     this
    1.38
     этой
    1.34
     denna
    1.27
    它
    1.27
     questa
    1.27
     এটির
    1.26
    Activations Density 0.577%

    No Known Activations