© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63770
    Prev
    Next
    INDEX
    Explanations

    shallow rendering with enzyme

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

    The neuron detects JavaScript/React unit‐test code patterns (e.g. imports of testing utilities like mount/shallow, describe/it blocks, etc.).

    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
    hao
    -0.76
     substation
    -0.73
     pulumi
    -0.73
    Columbus
    -0.72
    Geb
    -0.72
     Coachella
    -0.72
     embodi
    -0.71
    ticles
    -0.70
     vícti
    -0.69
    Levi
    -0.69
    POSITIVE LOGITS
     shallow
    1.67
    shallow
    1.51
     Shallow
    1.45
    Shallow
    1.44
     enzyme
    1.14
     Enzyme
    1.13
     wrapper
    1.12
    enzyme
    1.07
    wrapper
    1.01
    Enzyme
    1.00
    Activations Density 0.019%

    No Known Activations