© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11502
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to numeric tokens and measurements (digits, quantities, and units) in the text.

    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
     (-
    0.66
     $($
    0.65
     (.
    0.62
     (
    0.62
     (−
    0.61
     CGRect
    0.59
     மற்றும்
    0.58
     (!
    0.57
     または
    0.57
     ($(
    0.57
    POSITIVE LOGITS
    рная
    0.70
     skyrocketing
    0.70
     रीजन
    0.70
     posle
    0.68
     escritório
    0.68
    сная
    0.67
     Profes
    0.65
    warranty
    0.65
     antifreeze
    0.65
    viä
    0.64
    Activations Density 0.000%

    No Known Activations