© 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. 30864
    Prev
    Next
    INDEX
    Explanations

    forced labor and manpower

    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
     kov
    -0.82
    憊
    -0.76
    torrent
    -0.74
    laat
    -0.71
    ReadKey
    -0.70
     王子
    -0.70
    nosi
    -0.69
    惫
    -0.69
    arques
    -0.69
    Clients
    -0.69
    POSITIVE LOGITS
     labor
    4.81
     labour
    4.63
    labor
    3.42
     Labor
    3.33
    labour
    3.25
     Labour
    3.23
    Labor
    3.13
    Labour
    2.98
     laborers
    2.89
     LABOR
    2.88
    Activations Density 0.037%

    No Known Activations