© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49536
    Prev
    Next
    INDEX
    Explanations

    toxic abusive narcissistic relationships

    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
     diversa
    -0.79
     luxurious
    -0.78
     faggot
    -0.77
    洩
    -0.77
    tual
    -0.77
    一楼
    -0.76
     Dekker
    -0.76
     dorado
    -0.76
     thingy
    -0.75
    ้า
    -0.75
    POSITIVE LOGITS
     toxic
    2.61
     abusive
    2.03
     narcissistic
    1.94
    toxic
    1.88
     Toxic
    1.84
     narcis
    1.77
     токси
    1.76
     narcissist
    1.75
     toxicity
    1.70
     narciss
    1.66
    Activations Density 0.044%

    No Known Activations