© 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. 15546
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on floating‐point numeric tokens (numbers with decimal points).

    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
    та
    1.26
    ઉ
    0.98
    тали
    0.96
    ા
    0.93
    इन
    0.92
    ো
    0.91
    о
    0.86
    很多
    0.83
    inali
    0.83
    em
    0.82
    POSITIVE LOGITS
     Britannia
    0.82
     🙌
    0.80
     Haemat
    0.76
     Pharmacology
    0.75
     intervención
    0.74
     Producto
    0.74
     NotFound
    0.73
     Productos
    0.73
     Poverty
    0.73
     Hälfte
    0.73
    Activations Density 0.000%

    No Known Activations