© 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. 54155
    Prev
    Next
    INDEX
    Explanations

    heart failure and transplantation

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

    mentions of the term "heart" especially when it appears in medical contexts about heart conditions and treatments.

    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
    щик
    -0.80
     hardcore
    -0.79
    anı
    -0.78
    hou
    -0.77
    ロード
    -0.77
    ally
    -0.76
     хозя
    -0.75
     Steep
    -0.74
    鮰
    -0.73
     steep
    -0.73
    POSITIVE LOGITS
     failure
    1.15
     rate
    1.01
     Failure
    0.98
     attack
    0.91
     disease
    0.85
     attacks
    0.85
     Rate
    0.84
     FAILURE
    0.80
     February
    0.80
     rhythm
    0.79
    Activations Density 0.038%

    No Known Activations