© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40137
    Prev
    Next
    INDEX
    Explanations

    directory and file system access

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

    The neuron strongly activates on code references to the .NET filesystem API—especially instantiations of DirectoryInfo.

    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
    ilität
    -1.52
    ЛЮ
    -1.51
    электро
    -1.45
     at
    -1.44
    鲞
    -1.42
     there
    -1.38
     ссыл
    -1.35
    恺
    -1.31
     tại
    -1.29
    для
    -1.29
    POSITIVE LOGITS
    8
    1.66
     virš
    1.65
     farmacé
    1.64
    </h3>
    1.56
    ing
    1.52
    9
    1.51
     kaplama
    1.50
    "].
    1.47
     jį
    1.45
    6
    1.45
    Activations Density 0.050%

    No Known Activations