© 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. 86973
    Prev
    Next
    INDEX
    Explanations

    bread and baker

    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
    冰淇淋
    -0.95
     gelato
    -0.90
    쿡
    -0.86
     insurance
    -0.85
    Insurance
    -0.84
    insurance
    -0.84
     chocolates
    -0.82
     chocolate
    -0.81
    Chocolate
    -0.81
     gră
    -0.81
    POSITIVE LOGITS
     bread
    4.38
     Bread
    3.36
    Bread
    3.05
     breads
    2.97
    bread
    2.94
     loaf
    2.78
     loaves
    2.38
    🍞
    2.27
     BREAD
    2.23
     хлеб
    2.08
    Activations Density 0.016%

    No Known Activations