© 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. 37774
    Prev
    Next
    INDEX
    Explanations

    official rules and regulations

    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
     Direito
    -0.79
    neko
    -0.77
     poslední
    -0.75
     eggs
    -0.73
     evaluaciones
    -0.73
     rynku
    -0.72
    Allegro
    -0.72
     Análisis
    -0.71
    bjs
    -0.70
    𝟙
    -0.70
    POSITIVE LOGITS
     rules
    1.90
     Rules
    1.80
     guidelines
    1.77
     Guidelines
    1.59
     regulations
    1.58
     Manual
    1.53
    Rules
    1.53
     guide
    1.40
     Regulations
    1.38
     Handbook
    1.37
    Activations Density 0.055%

    No Known Activations