© 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. 10-GEMMASCOPE-RES-131K
    7. 71764
    Prev
    Next
    INDEX
    Explanations

    tuberculosis statistics and development

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

    technical or scientific terms in machine learning, programming, and biological 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_10/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
     two
    -1.84
     this
    -1.77
     after
    -1.71
     one
    -1.70
     providing
    -1.69
    遢
    -1.63
     their
    -1.61
     three
    -1.55
     bringing
    -1.54
     facilitating
    -1.54
    POSITIVE LOGITS
     You
    1.67
    ឵
    1.61
     как
    1.59
     для
    1.56
     craz
    1.51
     crappy
    1.49
     REALLY
    1.48
    สำหรับ
    1.44
     impos
    1.43
     VERY
    1.43
    Activations Density 0.002%

    No Known Activations