© 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. 99440
    Prev
    Next
    INDEX
    Explanations

    medication and dosage forms

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

    pharmaceutical dosage forms like tablets, capsules, and oral medications.

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

    The neuron detects pharmaceutical dosage and administration details, i.e. numbers paired with forms like “tablets,” “capsules,” “oral,” “daily,” etc.

    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
    ’
    -1.79
    f
    -1.73
     hatta
    -1.56
     الوز
    -1.47
     incluso
    -1.45
     kuni
    -1.44
     وانت
    -1.44
     menyen
    -1.43
     spesifik
    -1.41
    ckets
    -1.41
    POSITIVE LOGITS
     gesuchten
    1.66
     our
    1.57
     will
    1.52
    playera
    1.48
     будут
    1.48
     сейчас
    1.45
     Когда
    1.45
     vorliegenden
    1.44
     сегодня
    1.44
     Betrach
    1.41
    Activations Density 0.023%

    No Known Activations