© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens and symbols that form geographic coordinates (degrees, minutes, seconds) in text.

    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
    н
    0.81
     tailles
    0.80
    ură
    0.74
    தே
    0.71
    塚
    0.67
     サイズ
    0.66
     모양
    0.64
     sizes
    0.63
    Besides
    0.63
    Drugs
    0.63
    POSITIVE LOGITS
     Astrophysical
    0.79
     inkább
    0.79
    ждению
    0.78
    ะนั้น
    0.78
     истины
    0.74
    atakan
    0.74
    𝚑
    0.73
     amelyek
    0.73
     بأن
    0.72
     โอ้
    0.71
    Activations Density 0.003%

    No Known Activations