© 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. 33691
    Prev
    Next
    INDEX
    Explanations

    Glasgow City

    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
     deflation
    -0.76
     geschikt
    -0.71
    qwerty
    -0.71
    qtd
    -0.70
     Tai
    -0.67
    entlig
    -0.66
    Matriz
    -0.65
     gümüş
    -0.65
     appreciably
    -0.65
    ạng
    -0.64
    POSITIVE LOGITS
     Glasgow
    1.37
    Glasgow
    1.20
    glas
    0.90
     trow
    0.87
    Michigan
    0.85
     Lampung
    0.80
    Malawi
    0.80
     completar
    0.79
     Malawi
    0.78
    dziel
    0.77
    Activations Density 0.027%

    No Known Activations