© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9746
    Prev
    Next
    INDEX
    Explanations

    oral medication administration

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

    the administration route of medications, particularly identifying "orally" administered drugs and treatments.

    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_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
     his
    -1.46
    睏
    -1.36
     proviene
    -1.32
     generalmente
    -1.27
     they
    -1.27
     definida
    -1.27
    なども
    -1.25
    などが
    -1.23
     ajudá
    -1.23
     nawet
    -1.21
    POSITIVE LOGITS
    влении
    1.40
    staa
    1.31
    醱
    1.29
    isEqual
    1.26
    ACIÓN
    1.23
     derece
    1.23
    чих
    1.21
    zten
    1.20
    riss
    1.20
    istaa
    1.20
    Activations Density 0.225%

    No Known Activations