© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71422
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code snippets

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

    The neuron fires on HTML/XML tag delimiters—especially the opening “<…>” and closing “</…>” tags.

    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
     There
    -1.05
     because
    -1.04
     this
    -0.97
     difficult
    -0.96
     Although
    -0.96
     også
    -0.95
     Because
    -0.94
     completely
    -0.94
     one
    -0.94
    There
    -0.93
    POSITIVE LOGITS
     Jn
    0.95
     ww
    0.94
     '.
    0.93
    nta
    0.91
     rých
    0.91
    ovým
    0.90
    甚至是
    0.90
     mooie
    0.88
    YLON
    0.88
     dando
    0.88
    Activations Density 0.017%

    No Known Activations