© 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. 93497
    Prev
    Next
    INDEX
    Explanations

    WHO dose medicinal

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

    terminology related to medicine dosages and pharmaceutical information.

    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
    nasi
    -0.79
    VARIANT
    -0.79
     memu
    -0.76
     раду
    -0.76
     فتح
    -0.76
    tation
    -0.76
    eax
    -0.75
     Cardoso
    -0.74
     olig
    -0.73
    кість
    -0.72
    POSITIVE LOGITS
     dosage
    1.21
     route
    1.12
     dose
    1.07
     brand
    1.06
     generic
    1.02
     routes
    0.96
    Route
    0.95
    Generic
    0.94
     Route
    0.94
     administer
    0.93
    Activations Density 0.030%

    No Known Activations