© 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. 33670
    Prev
    Next
    INDEX
    Explanations

    HTML tags, code braces

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

    The neuron fires strongly on markup delimiters (e.g. HTML/XML tags, comment or CDATA openings).

    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
    也不敢
    -1.14
     soixante
    -1.11
     męska
    -1.08
     ventanas
    -1.06
     Provides
    -1.02
     gwia
    -0.98
     faute
    -0.97
     Modi
    -0.95
     modrá
    -0.94
    Exemplo
    -0.94
    POSITIVE LOGITS
     with
    1.16
     combining
    1.09
     fuper
    1.00
     poft
    1.00
    宜しくお願い
    0.99
     保証
    0.97
     if
    0.96
     verdura
    0.96
    ěte
    0.96
    キュリティ
    0.96
    Activations Density 0.025%

    No Known Activations