© 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. 473
    Prev
    Next
    INDEX
    Explanations

    air-fuel ratio

    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
    吃完
    -0.72
     pertes
    -0.69
    pago
    -0.68
    блемы
    -0.68
    findElement
    -0.68
    моно
    -0.68
    психо
    -0.67
    рующие
    -0.67
     mengh
    -0.65
     Вот
    -0.65
    POSITIVE LOGITS
     mixture
    1.96
     AFR
    1.62
     rich
    1.61
    mixture
    1.59
     Mixture
    1.55
     fuel
    1.55
     mixtures
    1.54
     richer
    1.52
     lean
    1.49
    fuel
    1.35
    Activations Density 0.037%

    No Known Activations