© 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. 65978
    Prev
    Next
    INDEX
    Explanations

    best award winner

    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
     野球
    -0.87
     electing
    -0.81
    āciju
    -0.80
     странах
    -0.79
    Forma
    -0.78
    Basin
    -0.77
     reminders
    -0.77
    CountryCode
    -0.77
    Kode
    -0.77
     chime
    -0.76
    POSITIVE LOGITS
     innovation
    1.17
     category
    1.16
     Large
    1.04
     Innovation
    0.96
     Best
    0.94
    Large
    0.91
     Initiative
    0.90
     Small
    0.88
     Team
    0.87
    Small
    0.87
    Activations Density 0.023%

    No Known Activations