© 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. 34-GEMMASCOPE-RES-131K
    4. 111065
    Prev
    Next
    INDEX
    Explanations

    Font Awesome icons, links, menu items

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

    The neuron is primarily triggered by icon‐related identifiers, especially Font Awesome class names (e.g. “fa”, “fa-users”, “fa-chevron-up”) and other “icon” tokens.

    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
    賞
    -0.83
     Valor
    -0.77
     teor
    -0.77
     线
    -0.77
     aceto
    -0.75
    κρα
    -0.75
     corpo
    -0.75
    weise
    -0.74
    astype
    -0.73
     Friendship
    -0.73
    POSITIVE LOGITS
     tree
    0.94
     trees
    0.84
     submenu
    0.83
     TreeNode
    0.81
     Collapse
    0.80
    treeview
    0.79
    SubMenu
    0.79
    mazon
    0.77
     menu
    0.76
     levels
    0.74
    Activations Density 0.005%

    No Known Activations