© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33035
    Prev
    Next
    INDEX
    Explanations

    introductions and reflections

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

    The neuron detects occurrences of JavaScript’s Reflect API method names (e.g., reflect.apply, reflect.construct, reflect.defineProperty, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     for
    -0.92
    tual
    -0.81
    叡
    -0.81
     unisex
    -0.78
     this
    -0.78
     jenis
    -0.78
    ()`
    -0.77
     çekilen
    -0.74
    unsubscribe
    -0.71
    mical
    -0.69
    POSITIVE LOGITS
    Reflect
    1.15
     reflector
    1.14
     Reflect
    1.03
     reflectors
    0.99
    Iš
    0.86
     reflecting
    0.85
    Опис
    0.82
    Periodo
    0.78
    nmgp
    0.77
    Imagens
    0.77
    Activations Density 0.011%

    No Known Activations