© 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. 34-GEMMASCOPE-RES-131K
    7. 90866
    Prev
    Next
    INDEX
    Explanations

    unit tests and expected results

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

    The neuron fires on occurrences of “Test” (especially import/package names, annotations, and identifiers) marking unit‐test declarations and related test‐framework tokens.

    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
     μή
    -0.85
    private
    -0.77
    coloured
    -0.77
    protected
    -0.75
     invention
    -0.75
    thoscope
    -0.75
     contains
    -0.74
    tams
    -0.73
     köt
    -0.73
    ApplicationTests
    -0.72
    POSITIVE LOGITS
     expected
    1.04
    expected
    0.99
     Expected
    0.92
    EXPECTED
    0.90
     Secre
    0.88
    Faça
    0.85
    Expected
    0.84
    စ်
    0.80
    法则
    0.80
    這裡
    0.80
    Activations Density 0.008%

    No Known Activations