© 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. 22-GEMMASCOPE-RES-131K
    7. 130558
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    scientific or medical terminology in technical research 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_22/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
    某些
    -0.96
    циали
    -0.95
     muuta
    -0.90
    我们会
    -0.84
     Clients
    -0.84
    heiro
    -0.81
    するため
    -0.79
    一方で
    -0.78
     miljö
    -0.77
      
    -0.77
    POSITIVE LOGITS
    聍
    0.89
     Gehir
    0.84
    ();
    0.83
    fordshire
    0.83
    vlá
    0.82
     oltre
    0.82
     drá
    0.82
    DAY
    0.81
    ртка
    0.81
    klinik
    0.80
    Activations Density 0.069%

    No Known Activations