© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7415
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens containing decimal points (floating-point numbers).

    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_31_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
    (:,:,
    0.79
    pairs
    0.64
     pairs
    0.62
    DICTION
    0.60
     Pairs
    0.59
    рена
    0.57
    getAsJsonObject
    0.55
     [{"
    0.55
    Pairs
    0.54
    [{
    0.53
    POSITIVE LOGITS
    ([-
    0.95
    =[-
    0.91
     range
    0.82
     =[
    0.82
    }([
    0.79
    }=[
    0.79
    range
    0.78
    Range
    0.76
     repeat
    0.75
     Range
    0.74
    Activations Density 0.013%

    No Known Activations