© 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. 92387
    Prev
    Next
    INDEX
    Explanations

    JavaScript module imports

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

    The neuron activates on occurrences of the CommonJS “require” keyword (i.e. module‐import calls).

    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
     bienvenue
    -0.90
    Drive
    -0.81
     xmax
    -0.80
    monte
    -0.79
     tamen
    -0.77
    Router
    -0.77
    ฐาน
    -0.77
     monte
    -0.76
    ymas
    -0.75
    gefahr
    -0.75
    POSITIVE LOGITS
    inven
    0.98
    bezpiec
    0.97
     некоторых
    0.93
     keju
    0.93
     dobré
    0.92
     szint
    0.90
     Terkait
    0.90
    sard
    0.89
    elegante
    0.87
    Opéra
    0.86
    Activations Density 0.003%

    No Known Activations