© 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. 55672
    Prev
    Next
    INDEX
    Explanations

    tax relief and qualifying investments

    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
     Revel
    -0.85
    ၌
    -0.81
    もしか
    -0.77
    Revel
    -0.74
     undersigned
    -0.74
     Strokes
    -0.74
    箭头
    -0.72
     Trails
    -0.72
    要不要
    -0.71
     Rub
    -0.70
    POSITIVE LOGITS
     reliefs
    1.18
     relief
    1.18
    Relief
    1.16
    relief
    1.04
     Relief
    0.99
     qualifying
    0.94
     tax
    0.93
     taxpayers
    0.92
     taxpayer
    0.91
     Ganze
    0.91
    Activations Density 0.016%

    No Known Activations