© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3665
    Prev
    Next
    INDEX
    Explanations

    virtual paths and folders

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

    This neuron detects XML configuration attributes and their values—e.g. names, IDs, paths, and related tokens in site/app settings.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     vents
    -1.21
     ventilación
    -1.01
     vent
    -1.00
     ventilation
    -0.94
     Ventilation
    -0.92
    Ventilation
    -0.85
     VENT
    -0.84
     Vent
    -0.84
    vents
    -0.82
    Vent
    -0.78
    POSITIVE LOGITS
     virtual
    1.49
     Virtual
    1.39
    Virtual
    1.34
     relative
    1.32
    virtual
    1.22
     Relative
    1.16
    Relative
    1.14
    relative
    1.11
     physical
    1.07
    虚拟
    1.04
    Activations Density 0.066%

    No Known Activations