© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13650
    Prev
    Next
    INDEX
    Explanations

    test setup and teardown

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

    The neuron fires on test‐framework lifecycle hook identifiers (e.g. setup/initialize and teardown/cleanup method names or annotations).

    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
    6
    -2.84
    7
    -2.83
     и
    -2.81
    8
    -2.70
    When
    -2.67
    2
    -2.66
    5
    -2.63
    9
    -2.61
    What
    -2.44
     και
    -2.44
    POSITIVE LOGITS
    臜
    2.81
     volledig
    2.72
    逦
    2.53
     bijna
    2.52
     vijf
    2.47
     verschill
    2.34
    薆
    2.34
    虓
    2.27
     eenvou
    2.20
     the
    2.19
    Activations Density 0.002%

    No Known Activations