© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44516
    Prev
    Next
    INDEX
    Explanations

    regex patterns and function calls

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

    This neuron detects uses of the identifier “test” (as in test(...) calls) in 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_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
     by
    -1.77
     from
    -1.71
    についての
    -1.65
     sofern
    -1.55
    馓
    -1.51
    ны
    -1.48
    饧
    -1.47
    迓
    -1.44
     dicha
    -1.41
     "
    -1.41
    POSITIVE LOGITS
    6
    2.19
    4
    2.05
    9
    1.80
    3
    1.77
    หรือ
    1.74
    oznam
    1.70
    8
    1.70
     atau
    1.65
    5
    1.63
    2
    1.57
    Activations Density 0.004%

    No Known Activations