© 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. 23696
    Prev
    Next
    INDEX
    Explanations

    universities or cities in Poland or Turkey

    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
     Warszawa
    -0.94
     Reykjav
    -0.93
     تهران
    -0.93
    Madrid
    -0.91
    Stockholm
    -0.90
     Praze
    -0.90
     Manila
    -0.90
     Helsinki
    -0.88
     Kyiv
    -0.88
     madrid
    -0.84
    POSITIVE LOGITS
     Regulations
    0.85
     NPY
    0.79
     undergraduates
    0.73
     Geelong
    0.73
    Rim
    0.72
     ECU
    0.71
     megy
    0.71
     이미
    0.69
     Radford
    0.69
     Universitäts
    0.68
    Activations Density 0.023%

    No Known Activations