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. 8272
    Prev
    Next
    INDEX
    Explanations

    clinical trial designs and analysis

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

    statistical and mathematical concepts in scientific research papers.

    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
    EEA
    -0.85
    ทุก
    -0.73
     bár
    -0.72
    霭
    -0.69
     travel
    -0.69
    мышлен
    -0.68
     bringing
    -0.68
    breve
    -0.68
    laş
    -0.67
     recovering
    -0.67
    POSITIVE LOGITS
     binomial
    1.26
     statistical
    1.11
     Bayesian
    1.09
     sampling
    1.00
     designs
    0.97
     ROC
    0.94
     Confidence
    0.90
     statisti
    0.89
    Designs
    0.84
     confidence
    0.83
    Activations Density 0.066%

    No Known Activations