© 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. 68073
    Prev
    Next
    INDEX
    Explanations

    javascript code/documentation

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

    The neuron is primarily detecting double‐quote characters that delimit attribute values in HTML tags.

    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
     wasn
    -1.77
     thrives
    -1.72
     avait
    -1.70
     retirada
    -1.59
     doivent
    -1.58
    是
    -1.56
    卨
    -1.55
     anún
    -1.53
     comenzará
    -1.53
     abarca
    -1.52
    POSITIVE LOGITS
    Appendix
    1.61
     hombros
    1.59
    \\
    1.59
    好评
    1.48
    .;
    1.46
    tedì
    1.46
    Aiheesta
    1.45
    %,
    1.45
     "]";
    1.45
    .,
    1.44
    Activations Density 0.001%

    No Known Activations