© 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. 22-GEMMASCOPE-RES-131K
    7. 14937
    Prev
    Next
    INDEX
    Explanations

    CSS text-align center

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

    The neuron fires on occurrences of “text-align: center” (i.e. centered‐text styling).

    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
    óbal
    -1.05
    で見る
    -1.04
     الشركة
    -0.98
     منذ
    -0.96
     daarvoor
    -0.95
    盌
    -0.95
    丅
    -0.94
    游戏的
    -0.94
     знаний
    -0.94
     requisite
    -0.93
    POSITIVE LOGITS
    INVISIBLE
    1.13
    に
    1.10
    𝐁
    1.04
    🔑
    1.02
     gjen
    1.01
    ёд
    0.98
     namen
    0.98
     nigra
    0.96
    cshtml
    0.93
     gjø
    0.92
    Activations Density 0.001%

    No Known Activations