© 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. 2458
    Prev
    Next
    INDEX
    Explanations

    cheese and its variants

    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
    ラメ
    -0.93
     materiais
    -0.83
     Lisbon
    -0.80
     materias
    -0.77
     sed
    -0.76
     strawberry
    -0.76
     SEK
    -0.76
     sediment
    -0.75
     glucose
    -0.75
     đình
    -0.75
    POSITIVE LOGITS
     cheese
    4.19
     cheeses
    3.11
    cheese
    3.08
    Cheese
    3.05
     Cheese
    3.03
    🧀
    2.53
    チーズ
    2.44
     cheddar
    2.23
     queijo
    1.88
     Cheddar
    1.87
    Activations Density 0.032%

    No Known Activations