© 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. 48156
    Prev
    Next
    INDEX
    Explanations

    Atacama, Chile, San Martín

    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
    ',)
    -0.81
    HZ
    -0.79
    シャツ
    -0.71
    риан
    -0.71
    计数
    -0.71
    crs
    -0.69
    southeast
    -0.69
    страницу
    -0.69
     Rousseau
    -0.69
    AHN
    -0.69
    POSITIVE LOGITS
     Chile
    2.06
    Chile
    1.86
     Chilean
    1.70
     Ata
    1.47
    Ata
    1.27
    chile
    1.17
     chileno
    1.09
     chilen
    1.07
     ESO
    1.02
     chile
    0.98
    Activations Density 0.069%

    No Known Activations