© 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. 38376
    Prev
    Next
    INDEX
    Explanations

    acute toxicity

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

    scientific or technical content related to toxicology, environmental science, and biological effects of chemicals.

    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
    ✥
    -0.91
    lilla
    -0.85
     beneficio
    -0.80
    entif
    -0.79
    preserve
    -0.77
    Crossref
    -0.77
     religieuses
    -0.77
     Émile
    -0.77
    patient
    -0.76
     portátiles
    -0.75
    POSITIVE LOGITS
     toxicity
    1.44
     toxic
    1.41
     exposure
    1.26
     detox
    1.24
     Toxicity
    1.21
     endpoints
    1.20
     endpoint
    1.13
     токси
    1.13
     toxicological
    1.13
    Toxic
    1.11
    Activations Density 0.175%

    No Known Activations