© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7470
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numerical expressions and measurements (e.g. fractions, dimensions, quantities, times).

    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
     Freeman
    0.85
     Fortress
    0.71
     fortress
    0.71
     souha
    0.70
     hoch
    0.69
     Ortiz
    0.69
     ‚
    0.68
     Bert
    0.66
     Meier
    0.66
     _______
    0.66
    POSITIVE LOGITS
    and
    0.80
    %>%
    0.80
    with
    0.77
    và
    0.75
    &&
    0.74
    for
    0.72
    of
    0.72
    ||
    0.69
    &+
    0.65
    while
    0.65
    Activations Density 0.301%

    No Known Activations