© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102629
    Prev
    Next
    INDEX
    Explanations

    red lipstick

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Résultat
    -0.81
    彩虹
    -0.79
     rinsing
    -0.74
    змы
    -0.73
    ANCIA
    -0.72
    asiun
    -0.72
     Créez
    -0.69
    ladelphia
    -0.69
    ggel
    -0.69
     hairst
    -0.68
    POSITIVE LOGITS
     lipstick
    2.53
     lips
    1.66
     lip
    1.60
     red
    1.59
    💄
    1.57
     Lipstick
    1.52
     Lip
    1.45
     Lipschitz
    1.27
    Lip
    1.22
    リップ
    1.20
    Activations Density 0.016%

    No Known Activations