© 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. 81417
    Prev
    Next
    INDEX
    Explanations

    automotive wiring harnesses

    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
     libc
    -0.84
     chalkboard
    -0.75
    mechan
    -0.73
     ASME
    -0.71
    鎵
    -0.71
    Hardware
    -0.70
    Cargar
    -0.69
    卫生
    -0.69
    uver
    -0.69
    ступил
    -0.69
    POSITIVE LOGITS
     harness
    2.25
    Harness
    1.95
     harnesses
    1.86
    harness
    1.83
     Harness
    1.75
     wiring
    1.73
     wires
    1.60
     wire
    1.59
     connectors
    1.44
    Wiring
    1.43
    Activations Density 0.011%

    No Known Activations