© 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. 22-GEMMASCOPE-RES-131K
    7. 15278
    Prev
    Next
    INDEX
    Explanations

    patient counts in medical studies

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

    numbers representing sample sizes in scientific studies.

    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_22/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
     even
    -1.70
     only
    -1.45
     could
    -1.43
     isn
    -1.40
     probably
    -1.38
     after
    -1.36
     usually
    -1.36
     may
    -1.29
     still
    -1.27
     seems
    -1.27
    POSITIVE LOGITS
     Secrétaire
    1.31
     Pristup
    1.30
     Спасибо
    1.20
     Vielen
    1.16
    komt
    1.16
    theres
    1.15
    Allah
    1.15
    vaila
    1.13
     bañera
    1.13
     Popis
    1.12
    Activations Density 0.274%

    No Known Activations