© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98946
    Prev
    Next
    INDEX
    Explanations

    temperature scales Celsius Fahrenheit

    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
    textwidth
    -0.69
     pirates
    -0.66
     factores
    -0.66
    ähne
    -0.66
     Sonnen
    -0.66
     рели
    -0.66
    laient
    -0.64
     muchacha
    -0.63
     hại
    -0.63
    캔
    -0.62
    POSITIVE LOGITS
     Fahrenheit
    1.20
     temperature
    1.13
     scales
    1.13
     scale
    1.11
     Celsius
    1.09
    Absolute
    1.08
     degrees
    1.03
     Scale
    1.03
     celsius
    1.00
     Absolute
    0.99
    Activations Density 0.019%

    No Known Activations