© 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. 48018
    Prev
    Next
    INDEX
    Explanations

    Object initialization `this`

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

    The neuron selectively fires on occurrences of the JavaScript/TypeScript `this` keyword (and adjacent object‐property access) in 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
    le
    -1.55
     even
    -1.43
    li
    -1.38
     affatto
    -1.35
    ne
    -1.35
    啷
    -1.34
    "
    -1.34
    ly
    -1.31
     Opposition
    -1.30
     evidenced
    -1.30
    POSITIVE LOGITS
     the
    1.41
    隳
    1.32
     quinze
    1.32
    енты
    1.30
    Fifteen
    1.29
    lesse
    1.27
    DÉ
    1.27
    Twenty
    1.26
    chable
    1.25
     スリーブ
    1.25
    Activations Density 0.001%

    No Known Activations