© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens with decimal points, i.e. 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
    ෑ
    0.70
    affirming
    0.70
    <0x89>
    0.69
    ären
    0.65
    ésar
    0.65
    ixeira
    0.64
    မ့်
    0.64
    varez
    0.63
     zahlreichen
    0.63
     wśród
    0.62
    POSITIVE LOGITS
    0
    1.87
    ０
    1.77
    ۰۰
    1.42
    ००
    1.30
    𝟬
    1.28
    ០០
    1.27
    ۰
    1.25
    ٠
    1.25
    𝟎
    1.23
    ০০
    1.19
    Activations Density 0.485%

    No Known Activations