© 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. 10-GEMMASCOPE-RES-131K
    7. 73557
    Prev
    Next
    INDEX
    Explanations

    prophylactic administration and trough levels

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

    medical or technical terms related to processes or treatments.

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

    The neuron primarily detects technical pharmacology terms—especially dosage‐related measurements (like “trough” levels) and preventive‐treatment words (like “prophylactic”)—in clinical or medical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    甞
    -2.75
    which
    -2.48
     berättar
    -2.41
     quand
    -2.41
    鷽
    -2.34
    臯
    -2.28
    瑧
    -2.27
    กับ
    -2.27
     vivía
    -2.25
     tropicales
    -2.16
    POSITIVE LOGITS
     Another
    2.81
     he
    2.70
    あります
    2.56
     About
    2.50
     of
    2.48
     Главная
    2.47
    The
    2.36
    
    2.36
     This
    2.34
    揶
    2.31
    Activations Density 0.011%

    No Known Activations