© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8662
    Prev
    Next
    INDEX
    Explanations

    wikipedia urls

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

    This neuron detects pieces of Wikipedia URLs (e.g. “en”, “wikipedia”, “org”, “wiki”, “/”).

    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
     \\
    -1.43
    </h2>
    -1.42
    ",
    -1.41
    ")]
    -1.39
     for
    -1.27
    /}{
    -1.27
    ',
    -1.27
    </td>
    -1.23
     represent
    -1.20
    </em>
    -1.19
    POSITIVE LOGITS
     tecnológicos
    1.54
    人たち
    1.50
     Interceptor
    1.38
     zatím
    1.37
     paillettes
    1.28
     brinquedos
    1.26
    ったのは
    1.25
    んだろう
    1.23
    ついで
    1.22
      -
    1.22
    Activations Density 0.065%

    No Known Activations