© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21949
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    The neuron is keyed to numeric tokens (i.e. numbers and numeric-like identifiers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.73
     of
    -1.53
     této
    -1.33
    れば
    -1.27
    igrette
    -1.24
    vielen
    -1.24
     for
    -1.23
    💼
    -1.23
    {?>
    -1.23
     on
    -1.20
    POSITIVE LOGITS
     their
    1.59
     is
    1.30
     I
    1.29
    涉及
    1.27
     It
    1.27
    \
    1.22
     \
    1.17
    :
    1.17
     ermöglich
    1.16
    It
    1.15
    Activations Density 0.099%

    No Known Activations