© 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. 66102
    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
    DEPTH
    -0.92
    ENOMEM
    -0.84
    เย็น
    -0.83
    拌
    -0.79
    кала
    -0.79
    owels
    -0.78
    Depth
    -0.78
     Error
    -0.77
     зару
    -0.77
    argue
    -0.77
    POSITIVE LOGITS
     sexual
    1.66
     grop
    1.59
     sexually
    1.59
     predatory
    1.48
     unwanted
    1.46
     inappropriate
    1.41
     objec
    1.36
     lewd
    1.36
    sexual
    1.32
     unwelcome
    1.30
    Activations Density 0.034%

    No Known Activations