© 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. 102913
    Prev
    Next
    INDEX
    Explanations

    acute and late toxicity grades

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

    medical terms related to treatment side effects, toxicity, and complications, particularly in cancer therapy.

    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
     conscious
    -0.80
     scented
    -0.78
     Slaughter
    -0.78
     cầu
    -0.75
    りましたが
    -0.73
    arias
    -0.73
     Luglio
    -0.73
    CHD
    -0.72
     colleges
    -0.71
    operators
    -0.71
    POSITIVE LOGITS
     toxicity
    1.70
     Grade
    1.37
     toxic
    1.34
     Toxicity
    1.27
    toxicity
    1.27
    Toxicity
    1.23
     grade
    1.19
    Grade
    1.13
     Grades
    1.06
    grade
    1.05
    Activations Density 0.187%

    No Known Activations