© 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. 16041
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens that are floating-point numbers (numbers with decimal points).

    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
    𝘇
    0.76
    こともある
    0.71
    EMANN
    0.70
     composée
    0.69
    اموش
    0.68
     serupa
    0.68
     verlieren
    0.68
     też
    0.68
    เรียก
    0.67
     étrangères
    0.67
    POSITIVE LOGITS
    ductory
    0.85
     品
    0.80
     Sunni
    0.79
    셔서
    0.78
    iye
    0.77
    lv
    0.74
    ointments
    0.74
     Маке
    0.73
     Ки
    0.73
     PwC
    0.73
    Activations Density 0.000%

    No Known Activations