© 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. 111271
    Prev
    Next
    INDEX
    Explanations

    React state and props

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

    references to React component state, particularly in declarations and assignments involving `state`, `setState`, `useState`, and `props`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     for
    -1.62
     první
    -1.57
     reminiscent
    -1.55
     июня
    -1.51
    淬
    -1.49
     immeasurable
    -1.48
     where
    -1.45
    cayaan
    -1.41
     onderwerp
    -1.41
    鉿
    -1.41
    POSITIVE LOGITS
    However
    1.73
     litri
    1.71
    “
    1.68
    『
    1.66
     lettera
    1.64
    mathrm
    1.60
    but
    1.55
    this
    1.52
    Nevertheless
    1.51
    Nonetheless
    1.49
    Activations Density 0.002%

    No Known Activations