© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 937
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numeric tokens, i.e. it fires on numbers appearing in the 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
     filePath
    0.85
    źć
    0.77
     jalan
    0.76
     Announced
    0.75
    تی
    0.71
    sprechend
    0.71
    媝
    0.70
    nia
    0.69
     dźwię
    0.69
    حات
    0.68
    POSITIVE LOGITS
    '*
    0.73
    മ്പോ
    0.70
    de
    0.67
     месяц
    0.67
    Вакан
    0.66
     которы
    0.66
     情
    0.66
     kuri
    0.65
    它们的
    0.64
    了大
    0.64
    Activations Density 0.003%

    No Known Activations