© 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. 22-GEMMASCOPE-RES-131K
    7. 128769
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to HTML/XML markup tags (i.e. text enclosed in “<…>”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    HTML attribute values and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     galeri
    -1.34
     kompetisi
    -1.28
     harap
    -1.20
     to
    -1.19
     Lokasi
    -1.15
     algas
    -1.14
     Komun
    -1.14
     bestia
    -1.14
     precau
    -1.12
    鬟
    -1.11
    POSITIVE LOGITS
     your
    1.27
    ımız
    1.14
     another
    1.07
     detalhes
    1.02
    ya
    1.01
     homicidio
    0.99
     cepillo
    0.98
    礦
    0.96
     suspensión
    0.96
     resize
    0.96
    Activations Density 0.005%

    No Known Activations