© 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. 38569
    Prev
    Next
    INDEX
    Explanations

    antenna diversity MIMO

    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
    ribu
    -0.74
     Billing
    -0.69
     Sat
    -0.69
     Fleet
    -0.67
    witch
    -0.66
    ț
    -0.66
    hib
    -0.64
     Ron
    -0.64
     Son
    -0.64
    hu
    -0.64
    POSITIVE LOGITS
     diversity
    1.67
    Diversity
    1.63
    diversity
    1.53
     Diversity
    1.52
     MIMO
    1.43
     antenna
    1.08
     diversidad
    0.99
    antenna
    0.96
     antennas
    0.96
    Antenna
    0.92
    Activations Density 0.038%

    No Known Activations