© 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. 10-GEMMASCOPE-RES-131K
    7. 65204
    Prev
    Next
    INDEX
    Explanations

    icons, css, animation, script

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

    This neuron activates on Font Awesome icon identifiers and related CSS prefixes (e.g. “far”, “fas”, “fa-css-prefix”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蛱
    -1.93
    旆
    -1.91
    鳢
    -1.86
    鼍
    -1.84
     to
    -1.81
    鼋
    -1.79
    砗
    -1.77
     potem
    -1.73
    敺
    -1.72
     anivers
    -1.71
    POSITIVE LOGITS
    –
    1.95
    er
    1.90
     –
    1.87
    ll
    1.77
    </strong>
    1.76
    i
    1.76
     všetky
    1.75
    ’
    1.70
    要知道
    1.70
    —
    1.67
    Activations Density 0.001%

    No Known Activations