© 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. 115983
    Prev
    Next
    INDEX
    Explanations

    private banking and family office

    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
     motel
    -0.79
    ovec
    -0.77
    jaci
    -0.76
     layui
    -0.76
    étisme
    -0.75
     vocales
    -0.75
     alıntı
    -0.75
    нитар
    -0.74
     nowrap
    -0.73
     ブーツ
    -0.73
    POSITIVE LOGITS
     wealth
    1.52
     Wealth
    1.45
    wealth
    1.41
     family
    1.35
    Wealth
    1.31
     Family
    1.22
     philanthropy
    1.08
     philanthropic
    1.07
    family
    1.05
     UH
    1.04
    Activations Density 0.023%

    No Known Activations