© 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. 117844
    Prev
    Next
    INDEX
    Explanations

    style and shopping suggestions

    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
    manjaro
    -0.87
     Въ
    -0.84
     ağ
    -0.81
     governing
    -0.79
    rents
    -0.79
    :=\
    -0.78
     Moq
    -0.78
     mellom
    -0.78
    单词
    -0.76
    poň
    -0.75
    POSITIVE LOGITS
     products
    1.48
     affordable
    1.23
     items
    1.22
     shopping
    1.21
     product
    1.21
     ideas
    1.20
     finds
    1.13
     suggestions
    1.12
     inspiration
    1.12
     steals
    1.11
    Activations Density 0.027%

    No Known Activations