© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11450
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily detecting numeric tokens—especially multi‐digit numbers and decimals (i.e. tokens containing sequences of digits, often 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
     Miłos
    0.77
     réactions
    0.77
    نك
    0.75
    ्रम
    0.74
     kinks
    0.73
    ందో
    0.73
    󠁥
    0.72
    itics
    0.71
     enfim
    0.71
     vendidos
    0.71
    POSITIVE LOGITS
    YS
    0.80
     PY
    0.76
    Unexpected
    0.76
    ز
    0.72
    ex
    0.69
    se
    0.68
    ни
    0.68
    ๕
    0.68
    Se
    0.68
    IS
    0.68
    Activations Density 0.000%

    No Known Activations