© 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. 48183
    Prev
    Next
    INDEX
    Explanations

    policies and procedures

    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
     démarrage
    -0.88
     može
    -0.86
    éroport
    -0.84
    Ergebnisse
    -0.81
     burials
    -0.80
     Tuhan
    -0.79
     levier
    -0.78
     nalazi
    -0.77
     läs
    -0.77
     naše
    -0.76
    POSITIVE LOGITS
     procedures
    4.34
     processes
    3.63
     procedure
    3.31
     policies
    3.11
     Procedures
    3.05
    procedures
    3.02
     protocols
    2.95
     systems
    2.88
    Procedures
    2.75
     mechanisms
    2.73
    Activations Density 0.073%

    No Known Activations