© 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. 90096
    Prev
    Next
    INDEX
    Explanations

    toxicity studies on animals

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

    scientific text about toxicology studies conducted on laboratory animals, particularly rats.

    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
    ęż
    -0.83
     diagnoses
    -0.81
     sputum
    -0.77
    ueta
    -0.75
     necessities
    -0.72
     سكانية
    -0.71
     potre
    -0.69
    ',['
    -0.69
     homemade
    -0.69
     cần
    -0.69
    POSITIVE LOGITS
     repeated
    1.05
     toxicity
    1.03
     repetir
    0.98
     repeat
    0.94
     Feeding
    0.94
    Feeding
    0.91
     studies
    0.91
    Repeated
    0.91
     Repeated
    0.90
     feeding
    0.87
    Activations Density 0.111%

    No Known Activations