© 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. 107595
    Prev
    Next
    INDEX
    Explanations

    household waste disposal

    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
     promis
    -0.80
     発
    -0.69
     summarizes
    -0.69
    sanitized
    -0.69
    ajuste
    -0.68
    issionais
    -0.67
    擁
    -0.67
    Résumé
    -0.66
     приложения
    -0.65
     трансформа
    -0.65
    POSITIVE LOGITS
     waste
    1.13
    Waste
    0.95
     Waste
    0.91
     Producer
    0.88
     Duty
    0.88
    Producer
    0.83
     WEE
    0.81
    waste
    0.81
    ătate
    0.81
    Duty
    0.79
    Activations Density 0.025%

    No Known Activations