© 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. 55611
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

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

    The neuron detects medical and anatomical terms, particularly those related to body parts, organs, and clinical procedures.

    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
     допусти
    -0.85
    studies
    -0.79
     summary
    -0.79
    blah
    -0.79
    another
    -0.77
    我最
    -0.77
     studies
    -0.76
     usein
    -0.76
     Wise
    -0.76
     identified
    -0.76
    POSITIVE LOGITS
     limes
    1.11
    Beaucoup
    0.96
     GIT
    0.94
     KV
    0.89
     localities
    0.88
    Якщо
    0.88
     provocation
    0.87
     modus
    0.86
     unbeatable
    0.86
    KV
    0.84
    Activations Density 0.729%

    No Known Activations