© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    bright and colorful descriptions

    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
     백
    -0.97
    Javadoc
    -0.93
     sepia
    -0.86
    백
    -0.81
    unknownFields
    -0.81
    Gray
    -0.77
    gray
    -0.77
     sanitario
    -0.77
     cerrar
    -0.77
    tinyos
    -0.77
    POSITIVE LOGITS
     colorful
    3.17
     colourful
    3.02
    colorful
    2.41
     Colorful
    2.34
     colored
    2.28
     brightly
    2.23
     colorido
    2.19
    Colorful
    2.17
     colors
    2.16
     coloured
    2.13
    Activations Density 0.055%

    No Known Activations