© 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. 60319
    Prev
    Next
    INDEX
    Explanations

    testing related to `junit`

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

    The neuron identifies the “.” separators in fully qualified names (e.g. the dots between Java package or import path segments).

    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
     kuiten
    -1.02
     erfüllen
    -0.95
     there
    -0.94
     inimes
    -0.94
    燴
    -0.91
     didst
    -0.88
     aasta
    -0.87
    логические
    -0.86
    另一个
    -0.86
    سرائ
    -0.86
    POSITIVE LOGITS
     test
    2.31
     tests
    1.98
    Test
    1.80
     Test
    1.75
     testing
    1.63
    test
    1.62
     Tests
    1.60
    测试
    1.51
    テスト
    1.49
     tested
    1.45
    Activations Density 0.003%

    No Known Activations