© 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. 22-GEMMASCOPE-RES-131K
    7. 129743
    Prev
    Next
    INDEX
    Explanations

    This neuron is strongly activated by HTML heading tags (e.g. `<h1>`, `<h2>`, `<h3>`, `<h4>`, `<h5>`).

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

    HTML heading 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
     belangrijk
    -1.35
     wielu
    -1.34
     나는
    -1.27
     nazwa
    -1.27
     kiedy
    -1.27
     goede
    -1.27
     見る
    -1.26
     expuesto
    -1.25
     waarmee
    -1.24
     folhe
    -1.23
    POSITIVE LOGITS
     kän
    1.75
     män
    1.67
     THEIR
    1.55
     ansik
    1.54
    oquia
    1.52
     parlement
    1.45
     Unito
    1.39
     rosse
    1.38
     egenskaper
    1.37
     henne
    1.35
    Activations Density 0.002%

    No Known Activations