© 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. 113569
    Prev
    Next
    INDEX
    Explanations

    associated with health outcomes

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

    phrases that express a relationship or association between concepts, particularly in scientific or academic 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
     for
    -2.42
     if
    -1.63
     to
    -1.63
     into
    -1.59
     without
    -1.46
     following
    -1.41
     through
    -1.33
     here
    -1.31
    pe
    -1.28
     followed
    -1.27
    POSITIVE LOGITS
    莅
    1.57
     Dijo
    1.52
     Geheimnis
    1.51
     kurzem
    1.50
    🧎
    1.48
    melody
    1.42
     rése
    1.41
    lahir
    1.39
     Vergnügen
    1.39
    
    1.37
    Activations Density 0.316%

    No Known Activations