© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20865
    Prev
    Next
    INDEX
    Explanations

    php conditional statements"}

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

    This neuron fires on the “{” tokens that start code blocks (i.e. opening curly braces).

    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
    $
    -2.06
    {
    -1.98
     is
    -1.70
    s
    -1.69
    \
    -1.59
    :
    -1.58
    '
    -1.49
    bruik
    -1.49
     to
    -1.46
    .
    -1.38
    POSITIVE LOGITS
     your
    2.14
    淠
    1.83
    を注文
    1.73
     sám
    1.71
     aquela
    1.67
     Ursachen
    1.55
     Ursache
    1.55
    寘
    1.53
     procédure
    1.53
    providedIn
    1.53
    Activations Density 0.005%

    No Known Activations