© 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. 53820
    Prev
    Next
    INDEX
    Explanations

    United States, kingdom, land

    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
     lifestyles
    -0.81
     Begins
    -0.76
     Midwest
    -0.76
    kyu
    -0.73
     begins
    -0.73
     processes
    -0.73
     bases
    -0.73
    pagest
    -0.71
     mercancías
    -0.70
     offers
    -0.69
    POSITIVE LOGITS
    Портал
    0.88
    Navig
    0.88
    Race
    0.86
    Navigation
    0.86
    Cette
    0.82
     TRAFFIC
    0.82
    Yoga
    0.82
    öz
    0.80
    Hep
    0.80
     RESOURCES
    0.79
    Activations Density 0.018%

    No Known Activations