© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98215
    Prev
    Next
    INDEX
    Explanations

    unit testing frameworks

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

    The neuron is triggered by occurrences of “test” (in class names, file paths, imports, etc.), i.e. tokens related to test code.

    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
     münchen
    -1.16
     armados
    -1.05
     História
    -1.03
     balón
    -1.01
     Lettres
    -1.00
     évé
    -1.00
    writeByte
    -1.00
     aynı
    -0.98
     Wikipédia
    -0.98
     lingü
    -0.97
    POSITIVE LOGITS
    ᆨ
    1.04
    Then
    1.01
    otient
    0.99
    rosis
    0.97
     dean
    0.95
    ով
    0.94
    chitis
    0.94
     emblematic
    0.94
    therefore
    0.93
     kp
    0.93
    Activations Density 0.003%

    No Known Activations