© 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. 11312
    Prev
    Next
    INDEX
    Explanations

    paired symbols and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on standalone numeric tokens—especially measurement values or data figures (integers and decimals).

    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
     !_
    0.64
     charisma
    0.57
    actment
    0.55
     selenium
    0.54
    [*]
    0.54
     Canadá
    0.52
     corpos
    0.52
     corpor
    0.51
    }^{*}-
    0.51
     extrême
    0.51
    POSITIVE LOGITS
    ((
    1.77
    =(
    1.69
     ((
    1.63
     $(
    1.55
    $(
    1.51
     [(
    1.51
    {(
    1.48
    ,(
    1.48
     =(
    1.45
    [(
    1.42
    Activations Density 0.084%

    No Known Activations