© 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. 34-GEMMASCOPE-RES-131K
    7. 2238
    Prev
    Next
    INDEX
    Explanations

    mkdir command / directory creation

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

    The neuron fires on mentions of creating directories or folders (e.g., “mkdir,” “folder,” “os.mkdir,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     directory
    -0.90
    дили
    -0.82
     deletion
    -0.80
    IfExists
    -0.76
     direction
    -0.75
    PDIR
    -0.74
    目录
    -0.73
    rmtree
    -0.72
     maintenance
    -0.71
    ÖN
    -0.71
    POSITIVE LOGITS
     mkdir
    1.57
    mkdir
    1.46
    MAKING
    0.98
     made
    0.91
     making
    0.90
    making
    0.89
    で作
    0.85
     maker
    0.82
    Making
    0.81
    maker
    0.79
    Activations Density 0.034%

    No Known Activations