© 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. 86921
    Prev
    Next
    INDEX
    Explanations

    air travel and UK destinations

    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
    цах
    -0.81
     domestic
    -0.81
     pembaca
    -0.79
    troppo
    -0.77
     alemão
    -0.74
     membros
    -0.73
     surpassing
    -0.71
     య
    -0.71
    Domestic
    -0.71
    URCH
    -0.70
    POSITIVE LOGITS
     Brexit
    1.04
    ocation
    0.84
     BU
    0.82
     summer
    0.81
    abortion
    0.81
    SHORT
    0.80
     Heathrow
    0.80
     UK
    0.79
    licante
    0.78
    ueve
    0.77
    Activations Density 0.023%

    No Known Activations