© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25255
    Prev
    Next
    INDEX
    Explanations

    closing html tags

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

    The neuron is highly responsive to HTML markup tags (especially structural ones like `<head>`, `</head>`, `<body>`, and `</body>`).

    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
    itzender
    -0.96
    кож
    -0.95
    listair
    -0.91
     sensibilité
    -0.90
     @"";
    -0.88
    ContentAlignment
    -0.87
    🇷
    -0.87
     Légion
    -0.87
    蚯
    -0.86
    HasMaxLength
    -0.85
    POSITIVE LOGITS
    elegante
    1.08
     donnera
    0.98
    我跟
    0.95
    <eos>
    0.94
    瞇
    0.87
    冇
    0.85
    .‏
    0.85
     sozialen
    0.84
    家に
    0.84
    ：……
    0.83
    Activations Density 0.004%

    No Known Activations