© 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. 103256
    Prev
    Next
    INDEX
    Explanations

    military, administrative, or regional entities

    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
    rolley
    -0.85
    __("
    -0.77
     Typography
    -0.77
    bois
    -0.75
     trabajadores
    -0.75
     Niveau
    -0.75
    Zubereitung
    -0.74
    SystemColors
    -0.74
    },{
    
    -0.72
    凛
    -0.71
    POSITIVE LOGITS
    ゝ
    0.76
    以来
    0.75
     Rump
    0.75
     Southern
    0.74
     Northern
    0.74
     Camp
    0.73
     northern
    0.73
     focusing
    0.71
    Trader
    0.71
     опера
    0.70
    Activations Density 0.003%

    No Known Activations