© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14989
    Prev
    Next
    INDEX
    Explanations

    medical, scientific, and specific terms

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

    HTML paragraph breaks or line spacing in formatted text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on “>” characters marking the ends of HTML/XML tags, i.e. it detects closing angle-brackets in markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     akku
    -1.23
     искать
    -1.18
     katt
    -1.14
    ⫸
    -1.12
     rajut
    -1.11
     kanton
    -1.09
     himmel
    -1.07
     ヴィトン
    -1.07
     kode
    -1.07
     menik
    -1.07
    POSITIVE LOGITS
    mis
    1.05
    𝑞
    1.00
    NO
    1.00
     सभी
    0.98
    ..........
    0.97
    ..."
    0.97
     Remedy
    0.97
     majority
    0.96
     Superhero
    0.96
    ar
    0.95
    Activations Density 0.003%

    No Known Activations