© 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. 116092
    Prev
    Next
    INDEX
    Explanations

    state-of-the-art technology and equipment

    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
    звичай
    -0.95
    ěř
    -0.94
     adım
    -0.90
     ponieważ
    -0.89
     歴史
    -0.88
     diferentes
    -0.87
     основ
    -0.87
    Hamster
    -0.86
    够了
    -0.86
    mejores
    -0.85
    POSITIVE LOGITS
     technology
    3.22
     technologies
    2.69
     techniques
    2.58
     equipment
    2.25
    technology
    2.09
     methods
    1.98
     Technology
    1.81
    Technology
    1.77
     tools
    1.73
     technological
    1.73
    Activations Density 0.095%

    No Known Activations