© 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. 4169
    Prev
    Next
    INDEX
    Explanations

    Norway and Norwegian

    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
     DKK
    -1.11
    Produktion
    -1.07
     hereof
    -0.94
    Webhook
    -0.94
    Wichtig
    -0.91
    Oltre
    -0.86
    huevos
    -0.86
     své
    -0.86
    lations
    -0.85
    Omg
    -0.84
    POSITIVE LOGITS
     arbej
    0.96
     kvinder
    0.93
    rätt
    0.90
    fören
    0.89
     kväll
    0.88
     hendes
    0.88
     torsdag
    0.88
     Norge
    0.86
     plads
    0.85
     bakgrund
    0.85
    Activations Density 0.042%

    No Known Activations