© 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. 84521
    Prev
    Next
    INDEX
    Explanations

    HTML stylesheet links

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

    The neuron detects HTML `<link>` tags that reference external CSS stylesheets (i.e. “link rel=… stylesheet … href=…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_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
    Leírás
    -1.23
    ͊
    -1.12
     arī
    -1.11
     vivió
    -1.05
     entró
    -1.03
     Voraussetzung
    -1.03
     obtuvo
    -1.00
     rifer
    -1.00
     дополнительные
    -0.99
     همچنین
    -0.97
    POSITIVE LOGITS
     bó
    1.02
     التالية
    1.02
     EDWARDS
    0.99
     sympa
    0.98
     formule
    0.97
    +",
    0.96
     conster
    0.95
    子は
    0.95
     xPos
    0.93
     palme
    0.93
    Activations Density 0.024%

    No Known Activations