© 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. 34-GEMMASCOPE-RES-131K
    7. 90352
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference

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

    The neuron is detecting occurrences of the standard module‐interop boilerplate identifiers—especially the “interopRequireDefault” pattern.

    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
    рата
    -0.90
    ㅈ
    -0.88
    дян
    -0.87
    ᾧ
    -0.78
    stle
    -0.78
    cadeira
    -0.77
    ocl
    -0.77
    =='
    -0.77
     discovered
    -0.76
    荆
    -0.74
    POSITIVE LOGITS
     module
    1.07
     Module
    1.02
    MODULE
    0.98
    imported
    0.98
    Imported
    0.94
    modules
    0.93
    avocat
    0.91
    module
    0.90
    Modul
    0.89
     MODULE
    0.88
    Activations Density 0.001%

    No Known Activations