© 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. 10-GEMMASCOPE-RES-131K
    7. 69238
    Prev
    Next
    INDEX
    Explanations

    class constructor definitions

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

    The neuron is triggered by JavaScript class constructor definitions (the “constructor” keyword and its surrounding class/extends/super context).

    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
    Öl
    -1.32
     napisał
    -1.30
     vermeld
    -1.30
    禤
    -1.28
     segurança
    -1.25
     Hauses
    -1.25
     został
    -1.24
     rivales
    -1.23
    нент
    -1.21
     restauración
    -1.20
    POSITIVE LOGITS
     Hinblick
    1.45
     as
    1.34
    They
    1.28
     use
    1.27
    錞
    1.22
     new
    1.20
     be
    1.19
    ),
    1.18
    While
    1.18
     status
    1.17
    Activations Density 0.014%

    No Known Activations