Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8137
    Prev
    Next
    INDEX
    Explanations

    dose-dependent effects and regimens

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

    mentions of medication doses or dose-response relationships in scientific/medical texts.

    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
     doses
    -1.09
     dosage
    -1.06
     dosages
    -1.05
    シ
    -0.99
    w
    -0.93
     dose
    -0.91
     rũ
    -0.89
    t
    -0.87
     дов
    -0.86
    ücken
    -0.85
    POSITIVE LOGITS
     of
    1.28
     regimen
    1.14
     administered
    1.11
    jść
    0.95
     escalation
    0.93
    bagi
    0.90
    béco
    0.90
    administered
    0.90
    ISTRATION
    0.88
     regimens
    0.86
    Activations Density 0.050%

    No Known Activations