© 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. 10-GEMMASCOPE-RES-131K
    7. 123533
    Prev
    Next
    INDEX
    Explanations

    stubbing out

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

    The neuron activates on mentions of “stub” in code or comments, i.e. references to code/test stubs.

    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
     einzige
    -1.91
    辚
    -1.91
    絝
    -1.90
     ehemalige
    -1.89
     sogenannte
    -1.77
     französische
    -1.76
    ordum
    -1.73
    剮
    -1.71
     größte
    -1.68
     icône
    -1.66
    POSITIVE LOGITS
    1
    2.86
    2
    2.42
    0
    2.27
    6
    2.16
    8
    2.14
    3
    2.13
    5
    2.13
    4
    2.00
    7
    1.91
     применяется
    1.81
    Activations Density 0.000%

    No Known Activations