© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9433
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—numbers, measurements, and decimal values.

    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
    measure
    0.91
    cure
    0.88
    5
    0.77
     crusade
    0.75
     metac
    0.75
    geme
    0.74
    ")),
    0.74
    universe
    0.73
     пяти
    0.73
     universe
    0.71
    POSITIVE LOGITS
    Για
    0.87
    الإ
    0.86
    нка
    0.80
    ふ
    0.80
    舴
    0.80
    مكن
    0.76
    刪
    0.75
    स्त्र
    0.75
    Якщо
    0.75
    Დ
    0.75
    Activations Density 0.000%

    No Known Activations