© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41561
    Prev
    Next
    INDEX
    Explanations

    /usr/local/ or /opt/ or /var/

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

    The neuron is triggered by forward‐slash characters, i.e. it detects file‐system paths or path separators in code.

    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
    0
    -2.28
     our
    -2.17
    _
    -1.98
    了很多
    -1.57
    しているので
    -1.52
     dlatego
    -1.47
     presentan
    -1.45
    ダース
    -1.44
     erläut
    -1.43
     רבים
    -1.42
    POSITIVE LOGITS
    見ても
    1.51
    vegetables
    1.46
    隂
    1.42
    diseño
    1.41
    迎来
    1.40
     reminding
    1.38
    expenses
    1.38
     ؛
    1.38
     Hô
    1.38
     They
    1.36
    Activations Density 0.028%

    No Known Activations