© 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. 83282
    Prev
    Next
    INDEX
    Explanations

    available colors and styles

    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
    這些
    -0.86
     NSCoder
    -0.83
    szönöm
    -0.83
    myra
    -0.80
    蔽
    -0.80
     войск
    -0.78
    servez
    -0.77
    regelen
    -0.76
    ânt
    -0.75
    jamento
    -0.73
    POSITIVE LOGITS
     colors
    2.69
     styles
    2.58
     colours
    2.53
     designs
    2.23
     sizes
    2.22
     color
    2.11
     colour
    1.90
     style
    1.90
    colors
    1.88
    styles
    1.81
    Activations Density 0.068%

    No Known Activations