© 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. 34464
    Prev
    Next
    INDEX
    Explanations

    css border and width properties

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

    The neuron activates on numeric attribute or style values—e.g. numbers used in tags or CSS properties like widths, heights, padding/margin, alignments, etc.

    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
    ッタリ
    -1.00
    قاط
    -0.98
    </sub>
    -0.98
    </sup>
    -0.96
    PostExecute
    -0.93
    סי
    -0.92
    enuta
    -0.92
    efined
    -0.91
     either
    -0.90
    昨晚
    -0.89
    POSITIVE LOGITS
     оружи
    1.09
    ıyorum
    1.03
     population
    0.96
    attva
    0.93
    hl
    0.93
    iteľ
    0.90
     mélanger
    0.90
    kozás
    0.90
    יסטוריה
    0.90
     ziren
    0.89
    Activations Density 0.038%

    No Known Activations