© 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. 104691
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

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

    This neuron detects C++ class declarations and their initializer‐list/inheritance syntax (e.g., the colon following a class or constructor).

    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
     péro
    -1.13
     vinho
    -1.10
     clube
    -0.94
     ع
    -0.92
    苼
    -0.90
     Kind
    -0.89
     cerve
    -0.88
    鲩
    -0.87
     queijo
    -0.87
     CONCLUSION
    -0.86
    POSITIVE LOGITS
     penutup
    1.04
     Turquía
    1.04
    ={()
    0.98
    ɸ
    0.96
     abarca
    0.96
    卻
    0.95
     forgot
    0.94
    örü
    0.90
     ilustrasi
    0.89
     can
    0.85
    Activations Density 0.605%

    No Known Activations