© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107863
    Prev
    Next
    INDEX
    Explanations

    assigning 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_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
    лиза
    -0.91
    diagram
    -0.85
    curve
    -0.84
    ="@+
    -0.82
    []){
    -0.81
    akang
    -0.81
     族
    -0.80
    такт
    -0.80
     doubt
    -0.79
    ="@
    -0.79
    POSITIVE LOGITS
     color
    1.99
     colors
    1.69
     colour
    1.48
     colours
    1.32
     Color
    1.29
    colormap
    1.28
    color
    1.23
     coloring
    1.22
    colorbar
    1.19
     colores
    1.17
    Activations Density 0.029%

    No Known Activations