© 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. 34-GEMMASCOPE-RES-131K
    7. 116097
    Prev
    Next
    INDEX
    Explanations

    medical treatment regimens

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

    medical treatment regimens and pharmaceutical terminology, especially drug names and chemotherapy protocols.

    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
     chré
    -0.88
    producción
    -0.85
     sitzen
    -0.82
    ള്ള
    -0.81
    륙
    -0.80
     Runtime
    -0.79
     Production
    -0.78
    iesti
    -0.77
    algunos
    -0.75
    PDATE
    -0.75
    POSITIVE LOGITS
     combination
    1.65
     regimen
    1.64
     combinations
    1.44
     regimens
    1.39
     combo
    1.30
     regime
    1.27
    Combination
    1.26
    combinations
    1.23
    combination
    1.20
     комбина
    1.19
    Activations Density 0.406%

    No Known Activations