© 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. 101667
    Prev
    Next
    INDEX
    Explanations

    component props

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

    the word "props" in programming code, particularly in JavaScript/React contexts where component properties are being passed or defined.

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

    The neuron fires on occurrences of the identifier “props” (i.e. references to component props in React code).

    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
     This
    -2.89
    ."
    -2.84
    ࿚
    -2.61
    at
    -2.42
    …)
    -2.39
     $
    -2.27
    拮
    -2.25
     were
    -2.25
     Only
    -2.22
    le
    -2.20
    POSITIVE LOGITS
    ﱠ
    2.98
    埽
    2.70
    汌
    2.69
    a
    2.55
    筇
    2.47
    怱
    2.45
    佧
    2.45
    Ꮷ
    2.42
    寕
    2.38
    慙
    2.36
    Activations Density 0.001%

    No Known Activations