© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78034
    Prev
    Next
    INDEX
    Explanations

    electrical boxes and utility infrastructure

    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
     carpets
    -0.73
    Kod
    -0.73
    YSTAL
    -0.70
    Congress
    -0.68
     slumber
    -0.68
    Obten
    -0.68
    новид
    -0.68
     outnumbered
    -0.67
     Twig
    -0.66
     Eko
    -0.66
    POSITIVE LOGITS
     electrical
    1.77
     electronics
    1.59
     control
    1.58
     junction
    1.58
     utility
    1.48
     Electrical
    1.48
     box
    1.42
     Utility
    1.41
     Control
    1.39
     boxes
    1.30
    Activations Density 0.051%

    No Known Activations