© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 379
    Prev
    Next
    INDEX
    Explanations

    infectious disease epidemiology

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

    academic citations in scientific papers, particularly author names and references.

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

    The neuron activates on four-digit numeric tokens (e.g., years or similarly formatted reference numbers).

    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
     cancer
    -0.85
     optical
    -0.83
    僧
    -0.82
     contenuto
    -0.80
     przes
    -0.79
     examination
    -0.78
     Eles
    -0.77
     operasi
    -0.77
     mineral
    -0.75
     regalo
    -0.73
    POSITIVE LOGITS
     infectious
    1.35
     Infectious
    1.22
     WHO
    1.03
    CDC
    1.02
    WHO
    1.02
    ectious
    1.01
     CDC
    0.98
     epidemio
    0.94
     PHE
    0.89
     Outbreak
    0.89
    Activations Density 0.050%

    No Known Activations