© 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. 34-GEMMASCOPE-RES-131K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    border styles and widths

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

    This neuron detects mentions of frames or borders in graphical UI or drawing code.

    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
     bless
    -0.79
     longitudinally
    -0.73
     Latvia
    -0.72
    ۙ
    -0.72
    ffix
    -0.68
     Zhejiang
    -0.68
    יבות
    -0.67
    Bless
    -0.67
    bind
    -0.67
    Але
    -0.66
    POSITIVE LOGITS
     lowered
    1.06
     bevel
    0.96
     dashed
    0.91
    Be
    0.90
    Raised
    0.88
     sunken
    0.87
    relief
    0.87
    matum
    0.86
     COMPOUND
    0.84
     raised
    0.84
    Activations Density 0.015%

    No Known Activations