© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56038
    Prev
    Next
    INDEX
    Explanations

    aviation repair and maintenance

    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
     GC
    -0.82
    studio
    -0.73
     tự
    -0.73
    cret
    -0.68
     MV
    -0.67
     nh
    -0.67
    有两
    -0.65
     extra
    -0.64
     GP
    -0.63
     GCC
    -0.63
    POSITIVE LOGITS
     repair
    1.43
     overhaul
    1.33
     maintenance
    1.31
    repair
    1.27
    Maintenance
    1.22
    Repair
    1.21
     repairs
    1.16
     MAINTENANCE
    1.16
    maintenance
    1.14
     Maintenance
    1.13
    Activations Density 0.023%

    No Known Activations