© 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. 34-GEMMASCOPE-RES-131K
    7. 93559
    Prev
    Next
    INDEX
    Explanations

    dose levels and quantities

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

    This neuron activates on medication dosing information, particularly when discussing appropriate doses, dosage ranges, or administration instructions in medical 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_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
    Выводы
    -0.93
     ارزش
    -0.90
    Ито
    -0.90
    Вывод
    -0.85
    譚
    -0.82
     ponts
    -0.82
     STATS
    -0.81
    Цели
    -0.81
    Плюсы
    -0.79
    Подготовка
    -0.77
    POSITIVE LOGITS
     dose
    4.06
     dosage
    3.91
     doses
    3.70
     dosages
    2.94
    dose
    2.91
     Dose
    2.63
    Dose
    2.61
     Dosage
    2.56
     dosing
    2.52
    Dosage
    2.42
    Activations Density 0.225%

    No Known Activations