© 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. 113527
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    technical or scientific terms, particularly chemical compounds and specialized terminology.

    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
    \
    -1.53
     dirait
    -1.41
     meilleurs
    -1.33
     抠
    -1.33
     choisis
    -1.30
     zaragoza
    -1.29
     légèrement
    -1.28
     invece
    -1.24
     eikä
    -1.23
     mourir
    -1.23
    POSITIVE LOGITS
     their
    2.17
     because
    1.95
     they
    1.94
     from
    1.91
     are
    1.63
     when
    1.63
     desde
    1.62
     они
    1.56
     through
    1.53
    because
    1.53
    Activations Density 0.348%

    No Known Activations