© 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. 99934
    Prev
    Next
    INDEX
    Explanations

    drug development and discovery

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

    vocabulary and concepts related to pharmaceutical drug development and 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
    ianza
    -0.90
     couronne
    -0.84
     personne
    -0.81
    readInt
    -0.80
     włos
    -0.80
     италья
    -0.79
    Katar
    -0.78
    氤
    -0.77
     pulsera
    -0.77
     Anat
    -0.75
    POSITIVE LOGITS
     drug
    1.94
     development
    1.83
     drugs
    1.57
     pharmaceutical
    1.45
    開発
    1.40
     discovery
    1.38
    drug
    1.30
     개발
    1.27
    drugs
    1.24
     Drug
    1.21
    Activations Density 0.128%

    No Known Activations