© 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. 86025
    Prev
    Next
    INDEX
    Explanations

    test followed by programming terms

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

    The neuron strongly activates on the standalone, capitalized token “Test,” as used in class names, file names, and comments.

    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
     unſ
    -2.30
     estábamos
    -2.22
    犼
    -2.19
    nın
    -2.16
    荭
    -2.13
     erstes
    -2.09
    '
    -2.09
    Türk
    -2.09
    Comes
    -2.05
    絝
    -2.05
    POSITIVE LOGITS
    in
    3.13
    ar
    2.78
    y
    2.67
    le
    2.50
    en
    2.39
    es
    2.34
    li
    2.33
    ll
    2.28
    d
    2.27
    ا
    2.22
    Activations Density 0.009%

    No Known Activations