© 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. 69893
    Prev
    Next
    INDEX
    Explanations

    world, european, asian, pan american

    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
     cansado
    -0.84
    menina
    -0.82
     digo
    -0.80
    yttä
    -0.79
    enetrable
    -0.76
     cuarta
    -0.75
     fuß
    -0.75
     digna
    -0.74
     competitivo
    -0.74
    おすすめの
    -0.74
    POSITIVE LOGITS
     World
    2.44
     European
    2.02
     world
    1.95
    World
    1.77
    orld
    1.48
     WORLD
    1.48
     Asian
    1.46
    European
    1.46
     Europe
    1.42
    世界
    1.38
    Activations Density 0.106%

    No Known Activations