© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100881
    Prev
    Next
    INDEX
    Explanations

    test suite names

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

    unit test-related imports and declarations in code (particularly JUnit Test annotations and testing framework imports).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting references to testing code constructs—especially “Test,” “TestCase,” and related testing framework imports or declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.42
     развитие
    -1.34
     out
    -1.31
     berdua
    -1.30
    igem
    -1.27
    了不少
    -1.26
     войны
    -1.23
    ̠
    -1.23
    "]));
    -1.23
    )...
    -1.22
    POSITIVE LOGITS
     такого
    1.58
    最强
    1.52
     colorear
    1.48
     oseb
    1.44
     terceros
    1.44
     posibil
    1.40
    МЫ
    1.35
    废话
    1.28
     vedno
    1.28
     تواند
    1.28
    Activations Density 0.008%

    No Known Activations