© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116076
    Prev
    Next
    INDEX
    Explanations

    security officer or Prime Minister

    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
    
    -0.98
    新人
    -0.84
     عنها
    -0.79
    
    -0.78
    侵略
    -0.73
    
    -0.73
    ]==
    -0.72
     tepi
    -0.71
    殃
    -0.71
    Ɔ
    -0.71
    POSITIVE LOGITS
     Sunday
    1.24
     vogliono
    0.86
     Tuesday
    0.86
    Coefficient
    0.85
    ่อน
    0.85
    eamiento
    0.84
    Sunday
    0.84
     Wednesday
    0.82
    miede
    0.82
    ポル
    0.81
    Activations Density 0.020%

    No Known Activations