© 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. 34-GEMMASCOPE-RES-131K
    7. 102753
    Prev
    Next
    INDEX
    Explanations

    CSS layout and appearance properties

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

    This neuron detects numeric literals in CSS style declarations.

    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
     from
    -0.91
    Fakta
    -0.85
     attentions
    -0.84
     недоста
    -0.84
    Destin
    -0.81
     comes
    -0.79
     που
    -0.79
    Provincial
    -0.78
     terrible
    -0.78
    ־ה
    -0.77
    POSITIVE LOGITS
    rset
    0.96
     фирмы
    0.96
     colgante
    0.94
    gier
    0.92
    њу
    0.92
    全体的に
    0.91
    艏
    0.91
     tredje
    0.91
    њи
    0.91
     тъ
    0.89
    Activations Density 0.028%

    No Known Activations