© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72795
    Prev
    Next
    INDEX
    Explanations

    medical procedures and technical terms

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

    technical terms related to medical procedures and computer operations.

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

    The neuron strongly fires on domain-specific technical jargon—especially medical procedure and specialized scientific terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    estries
    -0.85
     proiz
    -0.84
    penup
    -0.80
    orced
    -0.79
     reparti
    -0.78
     fiecare
    -0.78
     обов
    -0.78
     ActionResult
    -0.77
    relser
    -0.77
    眙
    -0.75
    POSITIVE LOGITS
     if
    1.08
     available
    1.08
     assuming
    1.05
     possible
    1.01
     without
    0.97
     simpler
    0.96
    できる
    0.94
     offered
    0.91
     routine
    0.90
     allowing
    0.90
    Activations Density 0.174%

    No Known Activations