© 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. 10-GEMMASCOPE-RES-131K
    4. 101778
    Prev
    Next
    INDEX
    Explanations

    royal family members and politicians

    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_10/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
     Vermögens
    -1.70
     Einrichtungen
    -1.59
     begleiten
    -1.54
     Aktionen
    -1.51
     Städten
    -1.48
     Regionen
    -1.47
     This
    -1.45
     einem
    -1.42
    対処
    -1.41
     bereits
    -1.36
    POSITIVE LOGITS
     decorativo
    1.45
    蚡
    1.45
     freio
    1.34
    cribes
    1.33
    футболка
    1.32
     amortecedor
    1.32
     geladeira
    1.30
    ynchronously
    1.30
     appui
    1.28
    关于
    1.27
    Activations Density 0.004%

    No Known Activations