© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110827
    Prev
    Next
    INDEX
    Explanations

    wine and food pairing

    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
     enfo
    -0.74
    remos
    -0.74
     assurer
    -0.72
    ρισ
    -0.71
    ests
    -0.70
    than
    -0.69
    付费
    -0.69
    hamshire
    -0.69
    raj
    -0.69
     permite
    -0.69
    POSITIVE LOGITS
    ைகள்
    0.92
     gạch
    0.87
    Hobbies
    0.86
    StreetMap
    0.82
     welder
    0.81
    tift
    0.81
    denes
    0.80
    
    0.79
    zca
    0.79
     fainted
    0.77
    Activations Density 0.013%

    No Known Activations