© 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. 10-GEMMASCOPE-RES-131K
    7. 42267
    Prev
    Next
    INDEX
    Explanations

    Florida and its associated locations

    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_10/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
    docker
    -1.54
    s
    -1.43
    ed
    -1.41
    ates
    -1.34
    ator
    -1.30
     defa
    -1.28
    Thanos
    -1.27
    th
    -1.25
    ate
    -1.23
    ned
    -1.22
    POSITIVE LOGITS
     Florida
    1.77
     would
    1.68
    florida
    1.57
    Florida
    1.54
     florida
    1.48
     quizás
    1.34
    тить
    1.27
     exclusively
    1.27
    AddRange
    1.27
    jeb
    1.27
    Activations Density 0.257%

    No Known Activations