© 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. 59462
    Prev
    Next
    INDEX
    Explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     him
    -1.12
    AddTagHelper
    -1.06
    赤い
    -1.03
    AxisAlignment
    -0.98
    geted
    -0.96
     aastal
    -0.95
    ようです
    -0.92
     führt
    -0.91
    ngulo
    -0.90
    usan
    -0.90
    POSITIVE LOGITS
     shades
    1.48
     color
    1.38
     tones
    1.37
     colors
    1.34
     hues
    1.30
     colour
    1.14
    ish
    1.13
     colours
    1.13
    dish
    1.12
     اللون
    1.11
    Activations Density 0.026%

    No Known Activations