© 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. 10-GEMMASCOPE-RES-131K
    7. 118992
    Prev
    Next
    INDEX
    Explanations

    code delimiters and markup

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

    closing angle brackets in HTML/XML tags.

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

    This neuron detects markup tags—that is, tokens representing HTML/XML element openers enclosed in “<…>.”

    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
    0
    -4.41
    3
    -3.61
    6
    -3.36
    8
    -3.31
    1
    -3.19
    After
    -3.16
    2
    -3.09
    Despite
    -3.03
    For
    -2.97
    7
    -2.97
    POSITIVE LOGITS
    ࿙
    3.19
     they
    2.86
    垕
    2.72
    栒
    2.67
    ୩
    2.66
    ſſel
    2.64
     zdroj
    2.55
    钐
    2.55
    >
    2.53
     แต่
    2.53
    Activations Density 0.004%

    No Known Activations