© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91247
    Prev
    Next
    INDEX
    Explanations

    city park names

    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
    
    -0.73
     Zweig
    -0.71
     succulents
    -0.71
    Нам
    -0.70
     Stol
    -0.70
     SSR
    -0.68
     seer
    -0.68
     Ceará
    -0.67
    Hei
    -0.66
     cilantro
    -0.66
    POSITIVE LOGITS
     Huntsville
    0.83
     Hartmann
    0.81
    iky
    0.79
    ✆
    0.77
     Covington
    0.77
    isca
    0.75
    ătă
    0.74
     Willoughby
    0.73
    тор
    0.71
     forests
    0.71
    Activations Density 0.028%

    No Known Activations