© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    file system attributes

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

    The neuron fires on low‐level filesystem jargon—terms related to data journaling, directories, inodes, and similar metadata concepts.

    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
     sown
    -0.82
    leyebilirsiniz
    -0.78
     rye
    -0.76
    ⊗
    -0.75
     הארץ
    -0.73
    ająca
    -0.73
    жку
    -0.73
    坪
    -0.72
    injected
    -0.72
    ceous
    -0.71
    POSITIVE LOGITS
     inode
    1.04
    inum
    1.03
    ACL
    0.95
     metadata
    0.93
     extended
    0.88
    inode
    0.85
     file
    0.85
     directory
    0.84
    metadata
    0.82
     Extended
    0.82
    Activations Density 0.091%

    No Known Activations