© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1875
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric values (digit sequences, including integers and decimals).

    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
    ײ
    0.70
     꿈
    0.69
     Taehyung
    0.69
    🐚
    0.69
     ð
    0.69
     ư
    0.66
    🌬
    0.66
     पंतप्रधान
    0.66
     גם
    0.66
    🌌
    0.65
    POSITIVE LOGITS
    <unused1838>
    0.82
    <unused490>
    0.79
    <unused99>
    0.75
    <unused480>
    0.74
    <unused462>
    0.73
    <unused458>
    0.71
    <unused497>
    0.70
    <unused1823>
    0.70
    <unused437>
    0.68
    <unused312>
    0.66
    Activations Density 0.002%

    No Known Activations