© 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. 73701
    Prev
    Next
    INDEX
    Explanations

    PATH environment variable

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

    The neuron detects occurrences of the system environment variable “PATH.”

    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
    This
    -3.06
    Since
    -2.61
    During
    -2.56
     После
    -2.53
    These
    -2.53
    With
    -2.45
    There
    -2.45
    残酷
    -2.42
     Undoubtedly
    -2.39
    By
    -2.38
    POSITIVE LOGITS
    s
    6.75
    的
    2.98
    犼
    2.95
    
    2.78
    黉
    2.75
    ی
    2.70
    鏷
    2.67
    ￪
    2.58
     ナイロン
    2.53
    ’
    2.52
    Activations Density 0.003%

    No Known Activations