© 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. 115623
    Prev
    Next
    INDEX
    Explanations

    manufacturing and industry

    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
    繇
    -0.97
    emb
    -0.91
     umane
    -0.90
    strukt
    -0.88
     MasterCard
    -0.88
    церт
    -0.88
    imageshack
    -0.86
    (/[
    -0.85
    роваться
    -0.83
    UMBIA
    -0.83
    POSITIVE LOGITS
    🏭
    1.19
     Processes
    1.04
     อา
    1.03
    entric
    1.03
     slecht
    1.02
    tiembre
    1.00
     duur
    0.99
    聍
    0.98
     process
    0.98
    .
    0.98
    Activations Density 0.022%

    No Known Activations