© 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. 22-GEMMASCOPE-RES-131K
    7. 36607
    Prev
    Next
    INDEX
    Explanations

    FontAwesome icons bootstrap Typeface MINUS

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

    The neuron fires on mentions of “FontAwesome,” i.e. references to the Font Awesome icon/font library.

    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
    ResponseDto
    -0.99
    ÁR
    -0.96
     Aufwand
    -0.96
    phemy
    -0.92
    ÁT
    -0.91
     ponieważ
    -0.90
    いきなり
    -0.90
     solchen
    -0.89
    EREO
    -0.88
     діяльності
    -0.88
    POSITIVE LOGITS
    坟
    0.90
     coroa
    0.89
     białe
    0.89
    nyez
    0.87
    <bos>
    0.86
    はこの
    0.85
     agrad
    0.83
     mulher
    0.83
     audit
    0.83
     doth
    0.83
    Activations Density 0.002%

    No Known Activations