© 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. 65689
    Prev
    Next
    INDEX
    Explanations

    px solid border

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

    This neuron detects CSS “border” declarations that specify pixel widths (e.g. “border: 1px solid …”).

    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
    konos
    -1.56
    獁
    -1.52
     TÉ
    -1.42
    鹟
    -1.40
     terwijl
    -1.38
    ㈯
    -1.35
    
    -1.35
     zelve
    -1.34
    鳚
    -1.34
    隳
    -1.34
    POSITIVE LOGITS
     D
    1.42
     C
    1.38
     S
    1.36
    w
    1.34
     M
    1.30
    c
    1.25
     F
    1.24
    C
    1.24
     R
    1.23
    q
    1.23
    Activations Density 0.003%

    No Known Activations