© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30819
    Prev
    Next
    INDEX
    Explanations

    code delimiters and imports

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

    The neuron fires on programming-style tokens (preprocessor directives, imports, angle brackets, punctuation, and numeric literals) characteristic of source 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_34/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
     razie
    -0.90
     artesanía
    -0.86
     éléments
    -0.86
     bolsos
    -0.84
    ไทย
    -0.84
    ázat
    -0.82
    usammen
    -0.82
    fillText
    -0.82
    炙
    -0.81
    asil
    -0.81
    POSITIVE LOGITS
     retVal
    0.79
    化作
    0.76
    ety
    0.73
    rnn
    0.73
    autoreleasepool
    0.69
    Responder
    0.69
    Rela
    0.69
    AppDelegate
    0.68
    Oso
    0.68
    Mí
    0.68
    Activations Density 0.035%

    No Known Activations