© 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. 34-GEMMASCOPE-RES-131K
    7. 506
    Prev
    Next
    INDEX
    Explanations

    <META> or <TITLE> tags

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

    The neuron activates on HTML document boilerplate and structural tags (e.g. DOCTYPE, <HTML>, <HEAD>, <TITLE>, <META>).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    MAC
    -0.82
    $('
    -0.77
    legacy
    -0.76
     inimes
    -0.76
     MAC
    -0.74
    QMetaType
    -0.72
     benö
    -0.72
    db
    -0.72
     regelmatig
    -0.71
    :%.
    -0.70
    POSITIVE LOGITS
    疖
    0.85
    rotten
    0.84
     INCLUDING
    0.82
    guet
    0.82
     WHITE
    0.82
     Zia
    0.81
    ƪ
    0.80
     ἐκ
    0.80
     légitime
    0.80
    чера
    0.79
    Activations Density 0.008%

    No Known Activations