© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2513
    Prev
    Next
    INDEX
    Explanations

    salad dressing

    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
     ketchup
    -0.82
    rsch
    -0.78
     butter
    -0.78
    型号
    -0.77
     банков
    -0.76
     cocoa
    -0.76
    滯
    -0.76
    innis
    -0.75
     tattoo
    -0.74
     spaghetti
    -0.74
    POSITIVE LOGITS
     dressing
    1.86
     Dressing
    1.75
    Dressing
    1.55
    dressing
    1.39
     vinaigrette
    1.38
     dressings
    1.34
     cr
    1.31
     Vina
    1.19
     Cr
    1.10
     vina
    0.98
    Activations Density 0.010%

    No Known Activations