© 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. 129183
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to wiki‐style link and citation syntax—i.e. tokens marking URLs, “Link,” parentheses around references, and similar hyperlink markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    link http opens citation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     allegedly
    -1.09
     since
    -1.09
     because
    -1.09
     have
    -1.05
     only
    -1.02
     furthermore
    -1.01
    をはじめ
    -1.00
     said
    -0.99
    ですが
    -0.97
     finally
    -0.95
    POSITIVE LOGITS
     précédente
    1.14
    あー
    1.13
    ようになって
    1.12
    誰が
    1.08
    からお
    1.07
     duża
    1.05
    際に
    1.05
     muhte
    1.04
    ほら
    1.03
     inaczej
    1.02
    Activations Density 0.004%

    No Known Activations