© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30998
    Prev
    Next
    INDEX
    Explanations

    .aspx pages

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

    The neuron is specialized to pick up code‐style tokens—especially string literals containing URLs, file paths, and file extensions (e.g. “Default.aspx” or other “://…” patterns).

    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
     Abe
    -0.82
    気が
    -0.78
     می‌
    -0.78
     عج
    -0.76
     Apache
    -0.76
     best
    -0.74
     Sporting
    -0.74
    進んで
    -0.74
    UpdateTime
    -0.73
     Glanz
    -0.73
    POSITIVE LOGITS
    aspx
    1.95
    ~/
    1.47
    default
    1.38
     default
    1.34
    Pages
    1.34
    Default
    1.27
     Default
    1.20
    tab
    1.04
     ~/
    0.96
    Forms
    0.87
    Activations Density 0.037%

    No Known Activations