© 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. 32318
    Prev
    Next
    INDEX
    Explanations

    poison, venom, toxicology

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

    medical toxicology and poisoning-related content, particularly involving substance ingestion, intoxication, and treatments.

    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
    Navigator
    -0.94
    Messenger
    -0.83
     tuberculosis
    -0.81
    infection
    -0.79
     infection
    -0.75
    멸
    -0.75
     explorer
    -0.74
     Navigator
    -0.73
     infectious
    -0.73
    virus
    -0.73
    POSITIVE LOGITS
     poison
    1.23
     Poison
    1.22
     antidote
    1.15
    poison
    1.12
    Poison
    1.05
     Toxicology
    1.03
     toxic
    1.00
     poisoning
    0.95
     toxicity
    0.93
    toxic
    0.93
    Activations Density 0.063%

    No Known Activations