© 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. 87005
    Prev
    Next
    INDEX
    Explanations

    city names and proper 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
    🤹
    -0.75
     üst
    -0.74
     Wirth
    -0.71
     Maca
    -0.71
     Bypass
    -0.70
     Zeal
    -0.70
     Asheville
    -0.69
    rons
    -0.69
    Ec
    -0.69
     Borno
    -0.69
    POSITIVE LOGITS
     Mississauga
    1.44
     Peel
    0.80
    issauga
    0.80
     Васи
    0.74
    Peel
    0.71
    tableLayoutPanel
    0.70
    chium
    0.69
    HICLE
    0.69
     Sicher
    0.69
    LBL
    0.68
    Activations Density 0.013%

    No Known Activations