© 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. 58116
    Prev
    Next
    INDEX
    Explanations

    wheat beer and craft beer

    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
    utos
    -0.74
     Eurovision
    -0.73
     wuß
    -0.71
    borg
    -0.70
    นวน
    -0.70
     chanel
    -0.69
     Armee
    -0.69
     excavator
    -0.68
     consular
    -0.68
     cuốn
    -0.68
    POSITIVE LOGITS
     wheat
    1.40
     craft
    1.18
     Wheat
    1.17
    Wheat
    1.05
     Belgian
    1.04
    wheat
    1.04
     Craft
    1.02
    Craft
    0.99
     Lamb
    0.96
     Weiss
    0.95
    Activations Density 0.029%

    No Known Activations