© 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. 102699
    Prev
    Next
    INDEX
    Explanations

    male life and career events

    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
     from
    -0.93
    SHO
    -0.88
     their
    -0.87
     概要
    -0.86
    ڄ
    -0.81
    eschön
    -0.80
    ēju
    -0.80
     now
    -0.80
     bringing
    -0.79
    års
    -0.79
    POSITIVE LOGITS
     worked
    2.11
     work
    1.95
     works
    1.87
     working
    1.76
     retired
    1.47
     bekerja
    1.41
     owned
    1.40
     работа
    1.35
     graduated
    1.33
    ทำงาน
    1.32
    Activations Density 0.019%

    No Known Activations