© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 532
    Prev
    Next
    INDEX
    Explanations

    The neuron is a detector for comma tokens (i.e. it fires strongly on commas).

    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
    ：
    0.52
    ，
    0.51
    )。
    0.50
    ،
    0.48
    ？
    0.47
    、
    0.47
    ։
    0.46
    .。
    0.43
    。</
    0.43
    POSITIVE LOGITS
     there
    1.02
     we
    0.97
     it
    0.89
    there
    0.81
     you
    0.72
     they
    0.70
     he
    0.65
     which
    0.64
     she
    0.64
     odnosno
    0.62
    Activations Density 1.026%

    No Known Activations