© 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. 22-GEMMASCOPE-RES-131K
    7. 15586
    Prev
    Next
    INDEX
    Explanations

    URLs and cloud regions

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

    This neuron fires on URL/hostname fragments—especially domain names and numeric path or region identifiers in URLs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    cedula
    -1.16
    ývá
    -1.13
    ก็
    -1.13
    ヌーピー
    -1.05
    スポンサーリンク
    -1.03
     hjemmes
    -0.97
    ではでは
    -0.97
    超出
    -0.96
    مدر
    -0.96
    dreamstime
    -0.94
    POSITIVE LOGITS
    EMPL
    1.08
     they
    1.03
     us
    1.00
     nosotros
    0.96
    で
    0.94
    preneurship
    0.93
     ''
    0.92
     technische
    0.91
    ContentLoaded
    0.90
     welcher
    0.89
    Activations Density 0.003%

    No Known Activations