© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64606
    Prev
    Next
    INDEX
    Explanations

    import and patch

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

    The neuron is detecting Python import lines that bring in mocking and patching utilities (e.g. “from unittest.mock import patch”).

    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
    legende
    -0.82
    Voiced
    -0.81
    Muri
    -0.79
    ﾞ
    -0.79
    appBar
    -0.78
    Avon
    -0.78
     bloat
    -0.77
    minu
    -0.77
    Punj
    -0.75
     lost
    -0.75
    POSITIVE LOGITS
    Side
    1.35
     Side
    1.23
     side
    1.21
    ().__
    1.07
    Magic
    1.05
    side
    1.05
     SIDE
    1.04
     patch
    1.00
    patch
    0.99
     patches
    0.99
    Activations Density 0.005%

    No Known Activations