© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73506
    Prev
    Next
    INDEX
    Explanations

    XML attributes and tags

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

    This neuron responds to XML/HTML markup tokens, i.e. the angle‐bracketed tag names and their attribute names/values.

    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
     menuju
    -0.78
    ivamente
    -0.76
     tagħ
    -0.73
    ≔
    -0.73
     Prat
    -0.73
    hound
    -0.73
     (!(
    -0.71
    ⊨
    -0.71
     Glan
    -0.69
    ঔ
    -0.69
    POSITIVE LOGITS
     revés
    0.79
    廃止
    0.77
    見えて
    0.73
     loi
    0.73
     scheme
    0.73
     jurado
    0.72
    ждены
    0.72
    domains
    0.71
     professionali
    0.71
     sumber
    0.70
    Activations Density 0.017%

    No Known Activations