© 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. 22-GEMMASCOPE-RES-131K
    7. 14920
    Prev
    Next
    INDEX
    Explanations

    mocking and testing

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

    This neuron activates on mentions of mocking frameworks or mock-related identifiers (e.g. “Moq,” “Mock,” “Mocks,” “Rhino Mocks,” “gomock”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    »-
    -1.13
     hébergement
    -1.12
    ="">
    -1.10
    》,
    -1.09
     météo
    -1.03
     pantal
    -0.99
     setTime
    -0.98
     gsx
    -0.98
     販売
    -0.97
     喜欢
    -0.97
    POSITIVE LOGITS
    lated
    0.95
     jedoch
    0.95
     of
    0.95
     colheres
    0.93
    widehat
    0.93
     néanmoins
    0.93
     Hauses
    0.90
     city
    0.89
     проходит
    0.89
    mockito
    0.86
    Activations Density 0.003%

    No Known Activations