© 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. 80790
    Prev
    Next
    INDEX
    Explanations

    testing keywords and frameworks

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

    The neuron is detecting leading indentation whitespace (i.e. the amount of space at the start of a line).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code patterns indicating unit tests, especially testing framework imports, annotations/attributes, and test class/method declarations in source files.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    whitespace indentation at the beginning of lines in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    ຍ
    -0.78
     Abbildung
    -0.75
    有り
    -0.72
    KAY
    -0.72
    つぶ
    -0.70
     neben
    -0.70
    蝶
    -0.69
    近くに
    -0.69
     Apoptosis
    -0.69
    潰
    -0.69
    POSITIVE LOGITS
    Assert
    1.98
     Assert
    1.82
     Moq
    1.05
     assert
    1.05
     asserting
    0.98
    fake
    0.97
    assert
    0.97
    Asser
    0.96
    Arrange
    0.94
     Test
    0.93
    Activations Density 0.019%

    No Known Activations