© 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. 43273
    Prev
    Next
    INDEX
    Explanations

    XML tags and structure

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

    The neuron activates on XML/HTML tag syntax (angle‐bracket delimiters and tag names/attributes).

    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
    rajz
    -1.33
     when
    -1.20
     Entfer
    -1.16
     عندما
    -1.16
     Können
    -1.13
     diskusi
    -1.12
     يجب
    -1.09
     letzt
    -1.07
     echten
    -1.05
     erfolgreichen
    -1.05
    POSITIVE LOGITS
     getPassword
    1.27
    การณ์
    1.20
     importante
    1.17
     such
    1.17
    neous
    1.15
    ұл
    1.14
     sprawy
    1.14
    lazione
    1.14
     xmlns
    1.13
    quíni
    1.12
    Activations Density 0.408%

    No Known Activations