© 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. 33238
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron detects occurrences of the “import” keyword in code (i.e. module import statements).

    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
     र
    -0.88
    ответ
    -0.88
     by
    -0.84
    ->___
    -0.79
    到着
    -0.79
    ョ
    -0.79
    oldown
    -0.78
     ProductService
    -0.77
    MUT
    -0.77
     additional
    -0.76
    POSITIVE LOGITS
     {
    1.04
     juxta
    0.88
     bese
    0.86
     huidige
    0.84
    iul
    0.84
     kuitenkin
    0.83
     rupiah
    0.83
    ompi
    0.82
     ROOF
    0.81
     Buku
    0.81
    Activations Density 0.003%

    No Known Activations