© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127924
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on occurrences of the identifier “Test” (and its plural “Tests”) in code (e.g. in class names, annotations, imports, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    code test classes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    了不少
    -1.08
    änning
    -1.03
    蛱
    -0.98
     HomeComponent
    -0.97
     Klagen
    -0.94
     &
    -0.91
     "
    -0.91
     ideen
    -0.90
     þe
    -0.90
    IDTH
    -0.90
    POSITIVE LOGITS
     verwal
    1.06
     disponibilidad
    1.05
     tratto
    1.05
     gepub
    1.05
    ruptedException
    1.04
     område
    1.03
     grabado
    1.03
    1.02
     beobachtet
    1.02
     его
    1.02
    Activations Density 0.006%
    No Known Activations