© 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. 66011
    Prev
    Next
    INDEX
    Explanations

    sexual harassment

    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
    Accès
    -0.98
     cuillère
    -0.89
     solder
    -0.85
     buhay
    -0.84
    شتر
    -0.82
     patriotic
    -0.82
    Paperback
    -0.82
    Spéc
    -0.81
     незавер
    -0.81
    Dés
    -0.79
    POSITIVE LOGITS
     sexual
    3.02
     harassment
    2.48
     Sexual
    2.42
    sexual
    2.28
    Sexual
    2.27
     workplace
    1.97
     Harassment
    1.89
     sexually
    1.80
     harass
    1.77
     harassed
    1.54
    Activations Density 0.040%

    No Known Activations