© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116222
    Prev
    Next
    INDEX
    Explanations

    medical measurements and demographics

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

    statistical data and measurement values in scientific papers, particularly when reporting numerical results with units or confidence intervals.

    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
     (
    -2.34
    。(
    -1.38
     However
    -1.30
     There
    -1.27
    ！（
    -1.25
    』（
    -1.20
    ✨:
    -1.19
    .
    -1.18
     these
    -1.17
     rígida
    -1.17
    POSITIVE LOGITS
    )
    2.06
     '')
    1.88
    ).
    1.87
     ...)
    1.74
     {})
    1.69
     "")
    1.68
     [])
    1.66
    ++)
    1.56
     '.')
    1.56
    ?)
    1.48
    Activations Density 0.274%

    No Known Activations