© 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. 102611
    Prev
    Next
    INDEX
    Explanations

    institutional names and known entities

    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
    points
    -0.69
     moft
    -0.68
    namespace
    -0.68
    жным
    -0.67
    shadow
    -0.67
     ships
    -0.66
    蚓
    -0.66
    aw
    -0.65
    genos
    -0.63
     Store
    -0.62
    POSITIVE LOGITS
     National
    1.02
     national
    0.90
    duate
    0.85
    National
    0.81
    布局
    0.81
     research
    0.81
    国立
    0.81
    NATIONAL
    0.80
     Research
    0.79
     universities
    0.79
    Activations Density 0.042%

    No Known Activations