© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77243
    Prev
    Next
    INDEX
    Explanations

    human trafficking and forced labor

    np_acts-logits-general · gemini-2.5-flash-lite

    human trafficking and exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     columnIndex
    0.47
     क्वालिटी
    0.46
     Intervals
    0.43
     sabiduría
    0.43
     vzduchu
    0.43
     reheating
    0.43
     Мак
    0.42
    뜸
    0.41
     আকাশের
    0.41
    榖
    0.40
    POSITIVE LOGITS
     slavery
    0.89
     Slavery
    0.82
     trafficking
    0.80
     Traff
    0.77
     slave
    0.70
    lavery
    0.70
     traffickers
    0.70
     esclav
    0.70
     Slave
    0.67
     traff
    0.66
    Activations Density 0.045%

    No Known Activations