© 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. 49989
    Prev
    Next
    INDEX
    Explanations

    ace followed by medical or other terms

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

    the word "ace" followed by various medical or technical terms.

    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
     nobody
    -0.75
    „
    -0.69
    没有人
    -0.69
    現役
    -0.68
     artwork
    -0.68
    barrow
    -0.68
    cosis
    -0.67
    颜
    -0.67
     teilen
    -0.66
    GEM
    -0.65
    POSITIVE LOGITS
    Ace
    1.05
     Ace
    1.02
    vedo
    0.92
     ACE
    0.91
     ace
    0.90
     Hardware
    0.88
     Ventura
    0.86
    Osob
    0.86
     Attorney
    0.85
     Besar
    0.85
    Activations Density 0.026%

    No Known Activations