© 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. 10-GEMMASCOPE-RES-131K
    7. 59540
    Prev
    Next
    INDEX
    Explanations

    code delimiters and separators

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

    This neuron detects inline HTML style attribute strings (e.g., the contents of style="…").

    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
    $
    -2.84
     schwere
    -2.58
    For
    -2.25
    A
    -2.22
     successes
    -2.19
     leichte
    -2.14
     klassische
    -2.13
    He
    -2.13
     zusätzliche
    -2.11
     mögliche
    -2.06
    POSITIVE LOGITS
    Ꝑ
    2.33
     They
    2.17
    </strong>
    2.11
    "}}>
    2.09
     rendus
    2.09
    葑
    2.03
    fordert
    2.00
    特斯拉
    1.99
    我还是
    1.95
    这不
    1.92
    Activations Density 0.002%

    No Known Activations