© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    Indian cuisine and food

    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
    RTDA
    -0.77
    ೃ
    -0.76
     dollari
    -0.74
    registro
    -0.74
     воск
    -0.74
     انا
    -0.73
    陰
    -0.73
    handle
    -0.72
     moulding
    -0.71
     Medit
    -0.71
    POSITIVE LOGITS
     Curry
    0.91
    Curry
    0.88
    ジット
    0.88
     curry
    0.87
     Banglades
    0.83
     takeaways
    0.82
     ActiveRecord
    0.81
     restaurant
    0.81
     takeaway
    0.81
     Partition
    0.80
    Activations Density 0.009%

    No Known Activations