Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8178
    Prev
    Next
    INDEX
    Explanations

    human trafficking

    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
     tanaman
    -0.82
    &
    
    -0.81
     latihan
    -0.77
     Testing
    -0.76
    竊
    -0.75
     sayur
    -0.74
    €)
    -0.74
    =)
    -0.72
    \\\
    -0.72
     ghosts
    -0.71
    POSITIVE LOGITS
     trafficking
    2.22
     traff
    2.06
     Trafficking
    1.85
     slavery
    1.58
     Slavery
    1.36
     slave
    1.32
    fficking
    1.31
     sex
    1.27
     victim
    1.26
     rescued
    1.23
    Activations Density 0.016%

    No Known Activations