© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15909
    Prev
    Next
    INDEX
    Explanations

    icons and technical terms

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

    This neuron activates on Font Awesome icon class identifiers in HTML (e.g. the "fa" or "fas" tokens and their accompanying code values).

    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
     what
    -1.77
     one
    -1.66
     through
    -1.56
     after
    -1.52
     by
    -1.51
     using
    -1.48
     any
    -1.45
     which
    -1.45
     where
    -1.44
     all
    -1.36
    POSITIVE LOGITS
     disgruntled
    1.64
     begu
    1.48
    ඍ
    1.41
     flamboyant
    1.39
    ༤
    1.39
     strikingly
    1.38
     ™
    1.36
     foll
    1.36
     Dinas
    1.35
     remarkably
    1.34
    Activations Density 0.000%

    No Known Activations