© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10837
    Prev
    Next
    INDEX
    Explanations

    This neuron detects standalone numeric tokens, especially multi‐digit 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
     Haring
    0.80
     Hox
    0.78
    \<
    0.74
    観察
    0.71
    有很多
    0.69
     desks
    0.69
    入
    0.69
    有一些
    0.68
    注目
    0.68
     sensibly
    0.66
    POSITIVE LOGITS
     компании
    0.77
    zeug
    0.76
    吳
    0.76
    fonction
    0.75
    webtoken
    0.74
    пред
    0.74
     известен
    0.73
     अजीत
    0.73
    msup
    0.73
    msub
    0.72
    Activations Density 0.003%

    No Known Activations