© 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. 55708
    Prev
    Next
    INDEX
    Explanations

    hot gashot exhaust gases

    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
    فية
    -0.79
     Liquid
    -0.79
     líquido
    -0.76
     condensed
    -0.71
    érir
    -0.70
     liquidated
    -0.69
    Liquid
    -0.68
     riduzione
    -0.68
    hnia
    -0.68
     líquidos
    -0.67
    POSITIVE LOGITS
     gas
    2.91
     gases
    2.66
     gaseous
    2.03
     Gas
    1.98
    Gas
    1.97
     Gases
    1.94
    gas
    1.86
     GAS
    1.79
     газо
    1.68
     گاز
    1.67
    Activations Density 0.138%

    No Known Activations