© 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. 34-GEMMASCOPE-RES-131K
    7. 47036
    Prev
    Next
    INDEX
    Explanations

    yellow and other colors

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    蓝
    -1.12
    Blue
    -1.09
    Gray
    -1.06
    BLUE
    -1.06
     bleu
    -1.02
     blue
    -1.02
     BLUE
    -1.01
    藍
    -1.00
     Blue
    -1.00
     Gray
    -0.96
    POSITIVE LOGITS
     yellow
    3.84
    yellow
    3.34
     Yellow
    3.33
    Yellow
    3.19
    YELLOW
    2.80
     YELLOW
    2.66
     жел
    2.53
    黄色
    2.48
    黄
    2.45
     yellows
    2.34
    Activations Density 0.056%

    No Known Activations