© 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. 34-GEMMASCOPE-RES-131K
    7. 23579
    Prev
    Next
    INDEX
    Explanations

    react component lifecycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    梳
    -0.94
    closeModal
    -0.83
    !
    -0.77
     verdades
    -0.77
     باقی
    -0.75
     dual
    -0.75
    marginVertical
    -0.75
    蝼
    -0.75
     getIs
    -0.73
     generar
    -0.72
    POSITIVE LOGITS
    react
    0.93
    componentDid
    0.92
    vVar
    0.90
    REACT
    0.87
    róleo
    0.83
    romp
    0.83
    ズム
    0.82
     statis
    0.81
     historiador
    0.81
    Ǘ
    0.80
    Activations Density 0.005%

    No Known Activations