© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98851
    Prev
    Next
    INDEX
    Explanations

    toxicity or related qualifiers

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

    references to toxicity or harmful properties of substances.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     trouvent
    -0.94
     Medik
    -0.88
    cetamol
    -0.83
     lendemain
    -0.81
    xu
    -0.79
     sebaik
    -0.79
     jakarta
    -0.78
    ituation
    -0.77
    tamol
    -0.77
    Conditions
    -0.77
    POSITIVE LOGITS
     toxic
    2.91
     toxicity
    2.84
     Toxicity
    2.14
    Toxicity
    2.06
    toxic
    1.94
     Toxic
    1.84
    toxicity
    1.80
     токси
    1.77
     poisonous
    1.77
     harmful
    1.72
    Activations Density 0.228%

    No Known Activations