© 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. 99361
    Prev
    Next
    INDEX
    Explanations

    clinical trials and development

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

    text related to clinical trials, pharmaceutical development, and medical research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron picks out the formal, highly structured language and metadata (dates, proper names, numbers) typical of corporate press‐release announcements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     chré
    -0.96
     pharmaceutical
    -0.84
     leerlingen
    -0.84
     každé
    -0.83
     bloemen
    -0.82
    רונות
    -0.79
    seiti
    -0.79
    专门
    -0.79
     esimerkiksi
    -0.79
     inſ
    -0.79
    POSITIVE LOGITS
     candidate
    1.13
     potential
    1.10
     development
    1.07
     potentially
    1.05
     programs
    0.96
     late
    0.95
     candidates
    0.94
     furthest
    0.92
     studies
    0.90
    età
    0.87
    Activations Density 0.035%

    No Known Activations