© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70276
    Prev
    Next
    INDEX
    Explanations

    Heart followed by medical or organizational terms

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

    The word "Heart" at the beginning of names, organizations, or medical 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
    inture
    -0.90
    ionization
    -0.88
    mparas
    -0.88
    poy
    -0.87
    ouac
    -0.86
    hou
    -0.85
    rinho
    -0.81
    ernas
    -0.81
     identity
    -0.80
    itigation
    -0.80
    POSITIVE LOGITS
    Heart
    1.59
     Heart
    1.55
     heart
    1.49
    heart
    1.34
     ❤️
    1.26
     ♥️
    1.25
     hearts
    1.25
     HEART
    1.24
     Hearts
    1.23
     心
    1.21
    Activations Density 0.029%

    No Known Activations