© 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. 53939
    Prev
    Next
    INDEX
    Explanations

    washington dc area teams

    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
    襖
    -0.79
     Care
    -0.77
    ENCOD
    -0.73
    mahal
    -0.73
    Cor
    -0.72
     Berlin
    -0.72
    тори
    -0.71
    Athens
    -0.70
    nguyen
    -0.70
    Generate
    -0.69
    POSITIVE LOGITS
     Chesapeake
    0.98
     Potomac
    0.93
     Calvert
    0.85
    isés
    0.84
     Orioles
    0.77
     yourselves
    0.77
     umbre
    0.77
     bushel
    0.76
     Jär
    0.74
     Orrell
    0.74
    Activations Density 0.011%

    No Known Activations