© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33341
    Prev
    Next
    INDEX
    Explanations

    CSS font-family property

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

    The neuron strongly activates on CSS font declarations (e.g. “font-family,” font weights, and font‐face definitions).

    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
    il
    -1.04
    latt
    -1.02
    把他
    -1.01
     yaptığı
    -0.98
    é
    -0.94
    ll
    -0.94
     categor
    -0.93
    on
    -0.93
    FromDate
    -0.93
    av
    -0.92
    POSITIVE LOGITS
    ции
    1.20
    ATIVA
    1.20
    Sommaire
    1.18
     rapat
    1.12
     Италијани
    1.11
    ⌉
    1.09
     pemuda
    1.09
    hhhh
    1.09
    種類
    1.06
    後記
    1.05
    Activations Density 0.003%

    No Known Activations