© 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. 49389
    Prev
    Next
    INDEX
    Explanations

    adenovirus, IV, Q, Oxford

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

    scientific and medical terminology, particularly in the context of vaccines, pharmaceuticals, and technical research.

    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
     Pfizer
    -0.93
     Latvi
    -0.76
    erna
    -0.74
    getJSON
    -0.73
    ɯ
    -0.73
    edo
    -0.72
    陶瓷
    -0.71
    itemID
    -0.71
     properly
    -0.70
    thouses
    -0.70
    POSITIVE LOGITS
     adeno
    1.07
     Oxford
    0.85
     imperialism
    0.82
    paused
    0.81
    옥
    0.81
     adultery
    0.77
    sells
    0.77
     Reised
    0.76
    ológia
    0.75
    Oxford
    0.75
    Activations Density 0.008%

    No Known Activations