© 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. 14991
    Prev
    Next
    INDEX
    Explanations

    This neuron selectively activates 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
    是多少
    0.84
    <0xBF>
    0.82
     erkl
    0.74
    isomer
    0.72
     isole
    0.71
     दीजिएगा
    0.71
     korrekt
    0.71
    льных
    0.70
    舢
    0.69
     লাগল
    0.68
    POSITIVE LOGITS
    sa
    0.68
     дизайн
    0.68
    يها
    0.66
    %%%
    0.65
     개념
    0.65
     स्मारक
    0.65
     შ
    0.64
     captivated
    0.64
    itution
    0.64
     uml
    0.64
    Activations Density 0.000%

    No Known Activations