© 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. 50170
    Prev
    Next
    INDEX
    Explanations

    cohort studies and longitudinal research

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

    references to research studies, particularly longitudinal studies with year ranges in their names.

    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
    Trat
    -0.87
    Anas
    -0.79
     spurred
    -0.79
     Anas
    -0.79
    ọn
    -0.74
     šte
    -0.74
    acağına
    -0.73
     približ
    -0.73
    uille
    -0.72
    Đối
    -0.72
    POSITIVE LOGITS
     cohort
    1.73
     longitudinal
    1.70
     cohorts
    1.34
     Cohort
    1.27
     participants
    1.27
     study
    1.25
     participant
    1.23
     Longitudinal
    1.20
    itudinal
    1.11
    cohort
    1.10
    Activations Density 0.288%

    No Known Activations