© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81191
    Prev
    Next
    INDEX
    Explanations

    drug development and safety

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

    terms related to drugs, pharmaceuticals, and FDA regulation.

    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
     waistband
    -0.77
     cryptocurrency
    -0.77
    berater
    -0.74
     tiendas
    -0.73
     '\''
    -0.71
    craft
    -0.70
    Fußball
    -0.70
     Invocation
    -0.69
    大好き
    -0.68
     Zool
    -0.68
    POSITIVE LOGITS
     FD
    1.16
     Food
    0.96
     adulter
    0.94
     tolerances
    0.82
    articles
    0.82
    altham
    0.79
     interstate
    0.78
    Food
    0.77
     mette
    0.75
     Pure
    0.75
    Activations Density 0.030%

    No Known Activations