© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on floating‐point numeric literals (numbers with a decimal point and digits after it).

    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
     restorations
    0.88
     Fakat
    0.82
     dislocations
    0.77
     prothorax
    0.77
    하고자
    0.76
     restores
    0.75
    ^[
    0.73
     протяжении
    0.73
    ことになる
    0.73
     природе
    0.72
    POSITIVE LOGITS
    rivi
    0.84
    𝙚
    0.82
    𝙀
    0.80
    Altitude
    0.79
    い
    0.79
     Monument
    0.79
    𝙤
    0.78
    𝑦
    0.77
    ا
    0.77
    Monument
    0.76
    Activations Density 0.000%

    No Known Activations