© 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. 83796
    Prev
    Next
    INDEX
    Explanations

    numbers and street 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
     Linnaeus
    -0.78
     セミ
    -0.78
     Westwood
    -0.78
    膠
    -0.77
     universite
    -0.76
    邨
    -0.76
    когда
    -0.75
     auditor
    -0.75
     barna
    -0.74
     Uptown
    -0.73
    POSITIVE LOGITS
     China
    0.74
     Chinatown
    0.73
     Downtown
    0.71
    fires
    0.70
    China
    0.67
     merchants
    0.66
     Nantes
    0.66
     Qian
    0.65
     predecessors
    0.65
     opium
    0.64
    Activations Density 0.057%

    No Known Activations