© 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. 110496
    Prev
    Next
    INDEX
    Explanations

    React code and usage

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

    the word "React" (the JavaScript library name).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects mentions of the identifier “React” (especially in import or class/package 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
     ‘
    -2.22
    ing
    -2.05
     (‘
    -2.02
     Unless
    -2.02
     meiner
    -2.00
    ,’
    -1.98
     nueve
    -1.96
     unteren
    -1.96
     According
    -1.92
     goin
    -1.91
    POSITIVE LOGITS
    呖
    2.56
    渃
    2.45
    镲
    2.44
    躝
    2.42
    zelfde
    2.36
     haki
    2.30
    quot
    2.22
    ｢
    2.17
     baumwolle
    2.14
    
    2.14
    Activations Density 0.005%

    No Known Activations