© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1053
    Prev
    Next
    INDEX
    Explanations

    air is drawn

    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
     what
    -0.77
     data
    -0.76
    ขาว
    -0.70
     As
    -0.70
    вку
    -0.69
     efficient
    -0.69
     maximize
    -0.67
     sizable
    -0.66
     current
    -0.66
    วาง
    -0.66
    POSITIVE LOGITS
    modelBuilder
    0.90
     outlet
    0.89
    ște
    0.88
    ḩ
    0.87
    '}),
    0.86
    
    0.85
    
    0.84
    
    0.83
    sockets
    0.81
    mín
    0.80
    Activations Density 0.008%

    No Known Activations