© 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. 110951
    Prev
    Next
    INDEX
    Explanations

    heat exchangers or exchange factors

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

    words related to heat exchange and ion transport systems.

    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
    カビ
    -0.77
    자가
    -0.73
     ajoutez
    -0.69
     franchise
    -0.67
    equ
    -0.67
     nigra
    -0.66
     अध
    -0.65
     cookie
    -0.65
     gånger
    -0.65
     करती
    -0.65
    POSITIVE LOGITS
     exchanger
    2.13
     exchange
    1.92
     exchangers
    1.90
    exchange
    1.65
     exchanges
    1.52
     exchanging
    1.50
     Exchange
    1.48
    Exchange
    1.41
     heat
    1.41
     EXCHANGE
    1.37
    Activations Density 0.050%

    No Known Activations