© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    PD Parkinson's Disease PDD PDT

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

    abbreviations and acronyms in parentheses like (PD), (PDT), (NSCLC), particularly in technical or medical contexts.

    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
    irchen
    -0.73
    手臂
    -0.71
    caling
    -0.68
    caled
    -0.68
    bahn
    -0.68
    ݨ
    -0.67
    翅
    -0.66
    Conclusión
    -0.66
    Fácil
    -0.66
    Necesito
    -0.65
    POSITIVE LOGITS
     PD
    4.69
     pd
    4.47
    PD
    4.44
    pd
    4.25
    Pd
    3.77
     Pd
    3.66
     Ped
    2.77
     ped
    2.64
     PDI
    2.63
    pds
    2.59
    Activations Density 0.073%

    No Known Activations