© 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. 5133
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on words immediately next to numeric expressions—i.e. it marks tokens that follow numbers or measurements.

    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
    ंमुळे
    0.86
    fois
    0.77
    픈
    0.76
    审美
    0.74
     inflict
    0.74
    єю
    0.73
    бр
    0.73
    迫
    0.72
    ğ
    0.72
    ademie
    0.71
    POSITIVE LOGITS
     iniciado
    0.79
     budd
    0.70
    tod
    0.70
     अनुबंध
    0.70
     grabado
    0.69
    ten
    0.69
     öğren
    0.69
     incluido
    0.68
    ຂອງທ່ານ
    0.68
     incluyendo
    0.67
    Activations Density 0.006%

    No Known Activations