© 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. 22-GEMMASCOPE-RES-131K
    7. 14745
    Prev
    Next
    INDEX
    Explanations

    javascript, typescript, and web development libraries

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

    The neuron fires on tokens naming major JavaScript libraries and frameworks (e.g. React, React Native, Angular, RxJS, Next, Redux, Node) in import statements.

    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
    yttää
    -1.20
     lampada
    -1.17
     brisa
    -1.16
     dialami
    -1.16
    şim
    -1.16
     paleta
    -1.15
     all
    -1.14
    ｻ
    -1.14
    〜！
    -1.14
     Países
    -1.13
    POSITIVE LOGITS
    _
    1.30
    haha
    1.24
     
    1.20
    Mvh
    1.18
    脍
    1.16
    大丈夫です
    1.13
    indicated
    1.13
     ۔
    1.11
    zelfde
    1.10
    фия
    1.09
    Activations Density 0.005%

    No Known Activations