© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11779
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens that are floating‐point numbers (numerical values with a decimal point).

    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
     sighs
    0.63
    ד
    0.62
    批评
    0.56
     прид
    0.55
     mislead
    0.55
     there
    0.55
    there
    0.54
     THERE
    0.54
    ULL
    0.54
     possibile
    0.53
    POSITIVE LOGITS
    을
    0.74
     را
    0.72
     histology
    0.72
     Inflammation
    0.72
     carboxyl
    0.69
    기와
    0.67
     histological
    0.65
     hő
    0.65
     elétrica
    0.64
     epithelial
    0.63
    Activations Density 0.000%

    No Known Activations