© 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. 101949
    Prev
    Next
    INDEX
    Explanations

    package declarations

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

    closing tags or self-closing tags in XML/HTML markup, particularly at the end of attribute declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is strongly triggered by the “/>” sequence that ends self-closing XML/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
     you
    -2.08
    providedIn
    -1.96
    MAXN
    -1.95
    =======
    -1.94
    ichtete
    -1.92
     &
    -1.80
    ================
    -1.78
    ObjectMeta
    -1.76
    cccccccc
    -1.75
    figcaption
    -1.75
    POSITIVE LOGITS
    ࿙
    2.34
    乆
    1.97
    ㈪
    1.95
    ᐠ
    1.93
     insanlar
    1.93
     ölü
    1.93
    比较好
    1.88
    pobla
    1.82
    Crear
    1.77
    Subgoals
    1.77
    Activations Density 0.008%

    No Known Activations