© 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. 7759
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric data—tokens that occur right before or around numbers, figures, 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
    c
    0.82
    с
    0.81
    cı
    0.76
    
    0.76
    kw
    0.75
    ş
    0.72
    us
    0.72
    ysm
    0.72
    ası
    0.71
    PMG
    0.71
    POSITIVE LOGITS
     Democr
    0.80
    🏚
    0.80
    btnInventory
    0.78
     Ради
    0.75
    閉店
    0.74
     Configuring
    0.74
    📡
    0.73
    Decor
    0.73
     furnishes
    0.73
    ∉
    0.73
    Activations Density 0.000%

    No Known Activations