© 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. 83829
    Prev
    Next
    INDEX
    Explanations

    airline class seating

    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
     epistem
    -0.82
    цах
    -0.78
    volent
    -0.78
     nắng
    -0.77
    观看
    -0.77
    ésil
    -0.77
    iscus
    -0.75
    adox
    -0.74
    branches
    -0.73
     sizable
    -0.73
    POSITIVE LOGITS
     class
    1.53
     seats
    1.20
     Business
    1.19
     seating
    1.17
     Economy
    1.17
    class
    1.11
    Business
    1.10
     CLASS
    1.07
     cabin
    1.05
     economy
    1.02
    Activations Density 0.013%

    No Known Activations