© 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. 2009
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens containing decimal points (floating-point numbers).

    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
    （
    0.89
    ：
    0.87
    :
    0.86
    <td>
    0.83
    <0x80>
    0.79
    Что
    0.79
    การ
    0.78
    \[
    0.77
    Вы
    0.74
    <div>
    0.74
    POSITIVE LOGITS
     also
    1.36
     sebagainya
    1.36
     tiež
    1.30
     seterusnya
    1.25
     também
    1.24
     ayrıca
    1.24
     others
    1.22
     anderen
    1.17
     ardından
    1.15
     també
    1.15
    Activations Density 0.625%

    No Known Activations