© 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. 10-GEMMASCOPE-RES-131K
    7. 20091
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    This neuron activates on self-closing tag endings (the “/>” sequence) in markup or XML/HTML-like code.

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

    self-closing tag endings in markup/XML-like code (the "/>" terminator).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    self-closing tags in markup and code (like `/>` in HTML, XML, and JSX).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    罽
    -2.23
     atak
    -1.90
    疴
    -1.88
     a
    -1.84
    蕺
    -1.83
    ⢫
    -1.82
     aqueles
    -1.80
    ᥬ
    -1.75
    䜣
    -1.74
    ⎔
    -1.72
    POSITIVE LOGITS
    From
    1.96
    ?”
    1.90
    Like
    1.88
     Because
    1.88
    In
    1.85
    Although
    1.84
     Wartawan
    1.84
    With
    1.81
    Having
    1.80
    Fifteen
    1.80
    Activations Density 0.002%

    No Known Activations