© 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. 10-GEMMASCOPE-RES-131K
    7. 13022
    Prev
    Next
    INDEX
    Explanations

    class inheritance and generic types

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

    This neuron detects occurrences of the keyword “extends” in generic type or class declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    跸
    -2.20
    犼
    -1.70
    珦
    -1.70
     rése
    -1.64
    拊
    -1.63
     grafik
    -1.63
    蚰
    -1.60
     elektronik
    -1.55
     geene
    -1.52
     Функ
    -1.52
    POSITIVE LOGITS
    This
    1.84
    }
    1.72
    1
    1.69
    6
    1.67
    4
    1.62
     Ahnung
    1.58
    2
    1.57
     increase
    1.57
     will
    1.52
    The
    1.51
    Activations Density 0.004%

    No Known Activations