© 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. 53917
    Prev
    Next
    INDEX
    Explanations

    supply chain and demand flow beginnings

    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
    continue
    -0.73
     ところ
    -0.73
     calyx
    -0.72
     employee
    -0.71
     Rhod
    -0.71
     coding
    -0.70
     Elder
    -0.69
     Employee
    -0.69
    時期
    -0.69
    訓練
    -0.68
    POSITIVE LOGITS
     postponement
    1.10
     Visibility
    1.10
    供应
    0.99
    Supply
    0.91
     SC
    0.90
     collaboration
    0.89
     Supply
    0.87
    运作
    0.86
     supply
    0.85
     SCM
    0.85
    Activations Density 0.020%

    No Known Activations