© 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. 11940
    Prev
    Next
    INDEX
    Explanations

    css styling and layout

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

    numeric values in CSS property declarations, particularly for spacing properties like margin and padding.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     Eliminar
    -1.94
    Törté
    -1.73
     sikkert
    -1.68
     valgt
    -1.68
     Acerca
    -1.66
     też
    -1.66
     alebo
    -1.65
     anbef
    -1.63
    Ahol
    -1.63
     utford
    -1.60
    POSITIVE LOGITS
    .
    2.27
    TintMode
    1.57
    ньому
    1.56
    xvii
    1.50
    </i>
    1.49
    ).
    1.48
    MAXN
    1.48
     you
    1.48
    xii
    1.47
     المزيد
    1.41
    Activations Density 0.014%

    No Known Activations