© 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. 50016
    Prev
    Next
    INDEX
    Explanations

    American Heart

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

    medical and cardiology-related terminology, particularly references to heart conditions and cardiovascular research.

    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
     lapar
    -0.79
     epidermal
    -0.79
    婪
    -0.77
     endometriosis
    -0.76
    innis
    -0.76
     sneezing
    -0.74
    Nm
    -0.73
     mucosal
    -0.70
    的精神
    -0.70
     perine
    -0.69
    POSITIVE LOGITS
     heart
    4.00
     Heart
    3.50
     cardiac
    3.44
    Heart
    3.19
    heart
    3.19
     cardio
    3.06
     HEART
    2.98
     Cardiac
    2.97
     hearts
    2.88
    HEART
    2.72
    Activations Density 1.200%

    No Known Activations