© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129729
    Prev
    Next
    INDEX
    Explanations

    urls and schemas

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

    The neuron fires on URI scheme indicators—especially “http://” in XML/HTML namespace and schema declarations.

    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
    ();
    -2.17
     '
    -1.95
    );
    -1.90
     wasn
    -1.73
     What
    -1.73
    ">
    -1.72
     It
    -1.66
     wouldn
    -1.66
     didn
    -1.64
    what
    -1.61
    POSITIVE LOGITS
     myös
    1.63
    ''',
    1.63
     maksimum
    1.57
     mineures
    1.55
     farbe
    1.52
     tromper
    1.48
     verminder
    1.47
     innymi
    1.45
    legging
    1.44
     maksi
    1.42
    Activations Density 0.039%

    No Known Activations