© 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. 128866
    Prev
    Next
    INDEX
    Explanations

    Go imports or package prefixes

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

    This neuron activates on programming‐language identifiers in import/module paths (e.g. “go”, “py”, “jave”).

    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
     for
    -1.49
     while
    -1.46
    璿
    -1.37
    の問題
    -1.37
     from
    -1.34
     have
    -1.33
    śmy
    -1.31
     เรา
    -1.30
    𓐍
    -1.29
    اعي
    -1.28
    POSITIVE LOGITS
    8
    1.91
    9
    1.71
    2
    1.65
    3
    1.64
    4
    1.62
    6
    1.47
    7
    1.45
    5
    1.43
     /
    1.38
     Twelve
    1.38
    Activations Density 0.128%

    No Known Activations