© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127638
    Prev
    Next
    INDEX
    Explanations

    This neuron detects “background” style declarations (e.g. XML/CSS background or background-color attributes).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    background color

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     our
    -1.05
     whose
    -1.01
    レーキ
    -0.99
    illiers
    -0.95
     where
    -0.94
     potrebbero
    -0.93
    SqlParameter
    -0.91
     silken
    -0.90
     cases
    -0.90
     enfrenta
    -0.89
    POSITIVE LOGITS
     varier
    1.12
     voler
    1.10
     neutre
    1.09
     nastro
    1.05
     zwart
    1.03
     beber
    1.02
     applau
    1.02
    ครื่อง
    1.02
     pittores
    1.02
     chinois
    1.01
    Activations Density 0.008%

    No Known Activations