© 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. 50026
    Prev
    Next
    INDEX
    Explanations

    military branches and supplies

    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
     проми
    -0.77
     맞
    -0.72
    Throwable
    -0.70
    Produit
    -0.70
     miniatura
    -0.70
     parental
    -0.69
    ماية
    -0.69
    Matri
    -0.69
     мәкалә
    -0.68
     работо
    -0.67
    POSITIVE LOGITS
     baggage
    1.38
     commiss
    1.24
     supply
    1.24
     Commiss
    1.23
    supply
    1.18
    Supply
    1.18
     forage
    1.13
    transport
    1.10
     Supply
    1.09
     foraging
    1.09
    Activations Density 0.048%

    No Known Activations