© 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. 22-GEMMASCOPE-RES-131K
    7. 13706
    Prev
    Next
    INDEX
    Explanations

    constructor calls involving `super`

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

    This neuron detects object‐oriented class and method definition patterns—especially inheritance (e.g. “extends”) and constructor or other function/declaration signatures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    بدون
    -0.96
    ومن
    -0.95
     sorprend
    -0.92
     удиви
    -0.87
    Ohne
    -0.85
    imų
    -0.85
     MAKES
    -0.85
     convierte
    -0.85
    Зе
    -0.85
    eſ
    -0.85
    POSITIVE LOGITS
     as
    1.14
     with
    0.97
    เดิม
    0.91
     previously
    0.88
     in
    0.88
     again
    0.87
     super
    0.87
     поми
    0.86
     besides
    0.86
    super
    0.86
    Activations Density 0.011%

    No Known Activations