© 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. 2736
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects numeric tokens—especially floating-point and large quantitative figures.

    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
     seraient
    0.77
     zouden
    0.76
     serían
    0.73
     />}/>
    0.72
     serait
    0.71
     sarebbe
    0.71
     }{
    0.69
     }}{
    0.68
     aventura
    0.68
     würden
    0.68
    POSITIVE LOGITS
    \{
    0.68
    $\{
    0.65
    \{(
    0.63
    ↵
    0.59
    \{\
    0.59
    <eos>
    0.58
    Pres
    0.58
    $\
    0.58
    ■
    0.58
    _{\{
    0.57
    Activations Density 0.004%

    No Known Activations