© 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. 33735
    Prev
    Next
    INDEX
    Explanations

    concoctions, elixirs, and medicines

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

    words related to potions, medicines, or magical substances.

    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
     geophysical
    -0.77
     对象
    -0.74
    vaded
    -0.73
    Lucifer
    -0.73
     penance
    -0.72
    presenter
    -0.72
    hardware
    -0.72
     Enrichment
    -0.70
    vited
    -0.70
     systém
    -0.70
    POSITIVE LOGITS
     conco
    2.17
     brew
    1.56
     potion
    1.52
     mixture
    1.52
     brewed
    1.46
     ingredients
    1.38
     potions
    1.34
     elixir
    1.31
     ingredient
    1.27
     mixtures
    1.27
    Activations Density 0.013%

    No Known Activations