© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2086
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric tokens representing floating‐point values (numbers containing a decimal point).

    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
     (=
    0.62
    .=
    0.60
    zelfde
    0.58
    ,
    0.57
    ţie
    0.57
    (!)
    0.57
    alyse
    0.56
     (!)
    0.56
    (
    0.56
     («
    0.55
    POSITIVE LOGITS
     ಕಳೆದ
    0.61
    На
    0.58
    지난
    0.55
    लेकिन
    0.54
     Đến
    0.54
    ぐ
    0.54
    Bạn
    0.52
    новение
    0.52
    সং
    0.51
    जिस
    0.51
    Activations Density 0.040%

    No Known Activations