© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to programming‐language tokens (identifiers, operators, numeric literals, and punctuation) rather than ordinary natural‐language words.

    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
    parseInt
    0.54
     operat
    0.54
    !==
    0.50
    UInteger
    0.48
    ్రీ
    0.47
     kork
    0.46
     olun
    0.45
     ===
    0.45
     alen
    0.45
     কাঠামো
    0.44
    POSITIVE LOGITS
     [&](
    1.05
     [](
    0.84
    stoi
    0.79
     {.
    0.78
     [&
    0.77
    std
    0.74
    reinterpret
    0.71
     std
    0.70
    {.
    0.70
    [](
    0.69
    Activations Density 0.005%

    No Known Activations