© 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. 4375
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on decimal‐number tokens (floating‐point numerals with a dot).

    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
    ក្រុមហ៊ុន
    0.59
    ບໍລິ
    0.57
    <unused64>
    0.56
     цієї
    0.55
    ഭവ
    0.55
    岘
    0.54
     በማ
    0.53
     товаров
    0.53
     значительно
    0.53
    いただいた
    0.53
    POSITIVE LOGITS
    一个
    0.68
     a
    0.63
     is
    0.57
    0.57
    anski
    0.55
     an
    0.54
     my
    0.54
    s
    0.54
     The
    0.54
    ’
    0.54
    Activations Density 0.000%

    No Known Activations