© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108483
    Prev
    Next
    INDEX
    Explanations

    burger buns and bread

    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
    mandu
    -0.75
     gelato
    -0.74
     ricotta
    -0.73
     presentará
    -0.72
    ˨
    -0.71
     salami
    -0.69
    uklu
    -0.68
     pepperoni
    -0.68
    grafías
    -0.67
     scheduling
    -0.67
    POSITIVE LOGITS
     bun
    2.48
     buns
    2.39
    bun
    1.69
    Bun
    1.69
     BUN
    1.60
     Bun
    1.59
     bread
    1.48
    BUN
    1.45
     brioche
    1.32
     Bread
    1.29
    Activations Density 0.010%

    No Known Activations