© 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. 33211
    Prev
    Next
    INDEX
    Explanations

    words starting with aero

    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
    底部
    -0.82
     pusat
    -0.79
    一部
    -0.75
     climá
    -0.72
    马逊
    -0.72
    あるので
    -0.72
    れる
    -0.71
     ervan
    -0.71
    ござ
    -0.71
    ämä
    -0.71
    POSITIVE LOGITS
    Aer
    1.23
     Aer
    1.23
     aer
    1.06
     Aero
    0.98
    Aero
    0.96
     аэро
    0.91
     aero
    0.88
    dynamic
    0.83
    ів
    0.80
    氧化
    0.79
    Activations Density 0.014%

    No Known Activations