© 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. 50362
    Prev
    Next
    INDEX
    Explanations

    temperature and Kelvin

    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
     lupa
    -0.81
     criteria
    -0.75
     excluded
    -0.74
     exclude
    -0.73
     guidelines
    -0.73
     menyen
    -0.73
    enderror
    -0.71
     Alp
    -0.70
    Frequency
    -0.68
    udra
    -0.68
    POSITIVE LOGITS
     Kelvin
    1.13
     absolute
    1.02
    Absolute
    0.99
    Kelvin
    0.99
    absolute
    0.97
     kel
    0.96
    kel
    0.91
    niche
    0.88
     Absolute
    0.87
     абсолю
    0.85
    Activations Density 0.015%

    No Known Activations