© 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. 22-GEMMASCOPE-RES-131K
    7. 9704
    Prev
    Next
    INDEX
    Explanations

    broadcast, update, alerta, error, rules

    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_22/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
    ฌ
    -0.85
     muere
    -0.84
    方も
    -0.84
    Transcripción
    -0.83
    сія
    -0.82
     السف
    -0.81
    Autres
    -0.79
     자
    -0.78
    ⓙ
    -0.77
     others
    -0.77
    POSITIVE LOGITS
     its
    1.50
     their
    1.02
    their
    0.96
     препарат
    0.93
    catalog
    0.92
     LiveData
    0.91
     שלהם
    0.91
     erős
    0.90
    其
    0.89
    üenza
    0.89
    Activations Density 0.151%

    No Known Activations