© 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. 34-GEMMASCOPE-RES-131K
    7. 65331
    Prev
    Next
    INDEX
    Explanations

    .attr and .call

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

    The neuron fires on D3.js-style method‐chaining tokens (e.g. “svg”, “g”, “.”, “data”, “enter”, “append”, “attr”)—in other words, D3 selection and chaining syntax.

    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
     Simulator
    -0.84
     parada
    -0.78
    pagesize
    -0.75
    🍞
    -0.73
    kező
    -0.69
    相変わらず
    -0.69
    getItem
    -0.68
    绛
    -0.68
    %;
    -0.67
     新年
    -0.66
    POSITIVE LOGITS
    attr
    0.95
    酶
    0.88
     attr
    0.87
     call
    0.86
     Jüng
    0.79
     Turbine
    0.79
    NSMutableArray
    0.77
    していきます
    0.77
    卅
    0.74
     Chaldean
    0.74
    Activations Density 0.022%

    No Known Activations