© 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. 5936
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens representing decimal numbers (i.e. tokens with digits and 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
    سى
    1.16
    onaise
    1.00
     kautta
    0.99
     fillet
    0.98
     hva
    0.95
     congregate
    0.92
    શ
    0.92
     sürekli
    0.92
     lahko
    0.91
     supuesto
    0.91
    POSITIVE LOGITS
    ה
    1.33
    و
    1.15
    आ
    1.13
    ла
    1.11
    Пре
    1.11
    По
    1.05
    এক
    1.02
    Су
    1.01
     diligently
    1.00
    க்கணக்கான
    0.99
    Activations Density 0.171%

    No Known Activations