© 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. 55897
    Prev
    Next
    INDEX
    Explanations

    web page titles and styles

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

    This neuron detects HTML stylesheet link tags (and similar elements) specifying the MIME type “text/css” (e.g. type="text/css").

    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
     volar
    -0.80
     nati
    -0.76
     sapi
    -0.73
     아니
    -0.70
     dinosau
    -0.70
     sympa
    -0.68
    戶
    -0.68
     posses
    -0.68
    思います
    -0.67
     santi
    -0.67
    POSITIVE LOGITS
     text
    1.44
    text
    1.27
     TEXT
    1.20
     Text
    0.99
    Text
    0.96
     treff
    0.92
    TEXT
    0.90
     тек
    0.87
    screen
    0.85
     texto
    0.84
    Activations Density 0.009%

    No Known Activations