© 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. 40906
    Prev
    Next
    INDEX
    Explanations

    jest testing framework

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

    This neuron fires on testing‐framework keywords and function calls (e.g. “jest,” “test,” “expect,” “beforeAll,” 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_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
    衚
    -1.83
    )’
    -1.63
    addPreferred
    -1.63
    ,’
    -1.59
    是什么意思
    -1.58
    ൅
    -1.57
    ?’
    -1.57
     asamblea
    -1.56
    !’
    -1.55
     شیپور
    -1.55
    POSITIVE LOGITS
    .
    1.60
    {
    1.59
     ligeramente
    1.59
    |"
    1.55
     añad
    1.52
    龉
    1.50
     veinte
    1.45
    ate
    1.42
    and
    1.41
     his
    1.41
    Activations Density 0.006%

    No Known Activations