© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30715
    Prev
    Next
    INDEX
    Explanations

    duck viruses

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

    references to duck or animal viruses in scientific/medical contexts.

    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
    gant
    -0.83
    貓
    -0.75
     sharks
    -0.75
    骰
    -0.74
    dien
    -0.74
     lizard
    -0.73
     gorilla
    -0.73
     anthropology
    -0.72
     kitten
    -0.72
     shrimp
    -0.72
    POSITIVE LOGITS
     duck
    2.59
     quack
    2.47
     Duck
    2.28
    Duck
    2.19
    duck
    2.06
    Quack
    2.05
     ducks
    2.02
    🦆
    1.95
     Ducks
    1.78
     waterfowl
    1.67
    Activations Density 0.023%

    No Known Activations