© 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. 58357
    Prev
    Next
    INDEX
    Explanations

    wine emulation

    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
     aguja
    -0.82
    heizung
    -0.82
     agujas
    -0.81
     father
    -0.73
     vna
    -0.73
    Odpo
    -0.73
    𝐤
    -0.72
     Digestion
    -0.71
    isert
    -0.70
     resins
    -0.70
    POSITIVE LOGITS
     Wine
    1.48
     WINE
    1.31
     compatibility
    1.27
     emulate
    1.27
     wine
    1.25
    Wine
    1.19
    wine
    1.17
     emulation
    1.13
     em
    1.04
     Wines
    0.98
    Activations Density 0.050%

    No Known Activations