© 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. 34-GEMMASCOPE-RES-131K
    7. 107979
    Prev
    Next
    INDEX
    Explanations

    XML tags or code elements

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

    This neuron detects the start of markup tags—that is, the “<” token used to open XML/HTML‐style elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     every
    -0.90
     just
    -0.81
    Trichloroethane
    -0.79
     though
    -0.77
     Every
    -0.76
    urement
    -0.75
     before
    -0.75
     Igual
    -0.75
    競技
    -0.74
    endencias
    -0.74
    POSITIVE LOGITS
    </b>
    0.85
     ailing
    0.85
    行星
    0.81
     Chúng
    0.81
    了过去
    0.80
     Xin
    0.79
     encontrada
    0.78
    ei
    0.77
     densidad
    0.77
     probabilidad
    0.77
    Activations Density 0.033%

    No Known Activations