© 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. 22-GEMMASCOPE-RES-131K
    7. 70716
    Prev
    Next
    INDEX
    Explanations

    HTML tags, code, multilingual UI labels

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

    This neuron detects document section headings or titles marked up by heading tags (e.g. <h1>, <h2>, legend, etc.).

    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
    めます
    -1.02
     rev
    -1.02
    erweise
    -1.02
    :
    -0.98
    reté
    -0.98
    婢
    -0.95
    ktör
    -0.95
    ecutable
    -0.94
     Aseg
    -0.94
    StatusLabel
    -0.92
    POSITIVE LOGITS
     your
    1.47
     you
    1.09
     about
    1.03
    </caption>
    0.99
     investigation
    0.96
     समस्या
    0.96
    cillary
    0.94
    notations
    0.93
     Ль
    0.92
    になりました
    0.91
    Activations Density 0.010%

    No Known Activations