© 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. 98811
    Prev
    Next
    INDEX
    Explanations

    heat transfer and exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    况
    -0.87
    薬
    -0.81
    ITOS
    -0.81
    uminescence
    -0.81
     Artur
    -0.80
     landlord
    -0.77
     hoods
    -0.77
     Mapp
    -0.77
     mith
    -0.77
     WAT
    -0.77
    POSITIVE LOGITS
     transfer
    0.88
    MICA
    0.84
     balance
    0.83
     flux
    0.77
     pipe
    0.75
     mưa
    0.72
     '../../../../
    0.71
     content
    0.71
     неправи
    0.70
    signment
    0.69
    Activations Density 0.027%

    No Known Activations