© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44091
    Prev
    Next
    INDEX
    Explanations

    accessing component props

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

    The neuron detects occurrences of the React “this.props.” property‐access pattern (i.e. references to this.props and its following dot).

    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
    ⟣
    -2.13
     reseña
    -1.99
     samoz
    -1.95
    enziali
    -1.91
    恹
    -1.88
    Holstein
    -1.86
     mijn
    -1.86
     Atención
    -1.85
     profesora
    -1.84
    ва
    -1.83
    POSITIVE LOGITS
     which
    2.63
     it
    2.58
     of
    2.33
     until
    2.00
     We
    1.99
     from
    1.95
     although
    1.91
     comprised
    1.87
     this
    1.86
     one
    1.86
    Activations Density 0.002%

    No Known Activations