© 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. 34-GEMMASCOPE-RES-131K
    7. 32481
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

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

    The neuron spikes on code operator and punctuation tokens—things like “=>”, “!’, parentheses, braces, and other operator symbols.

    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
    ReadInt
    -0.89
     sencillos
    -0.88
     שת
    -0.87
    倆
    -0.85
    πον
    -0.85
    都沒有
    -0.84
    fordable
    -0.83
    ঈ
    -0.82
     powodu
    -0.82
     encontraron
    -0.82
    POSITIVE LOGITS
    CALL
    1.15
     calling
    1.13
     call
    1.13
     calls
    0.95
     CALL
    0.91
    Invoker
    0.88
    call
    0.87
    isFunction
    0.87
    Call
    0.86
    调用
    0.86
    Activations Density 0.020%

    No Known Activations