© 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. 41411
    Prev
    Next
    INDEX
    Explanations

    room for

    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
     to
    -2.55
            
    -1.78
    './
    -1.72
     most
    -1.72
     tramonto
    -1.66
     basierend
    -1.66
     zumal
    -1.64
     本
    -1.63
    MERS
    -1.62
    缫
    -1.60
    POSITIVE LOGITS
    Kedua
    2.13
    </h2>
    2.03
    Kemudian
    1.86
    Sedangkan
    1.71
    Semoga
    1.68
    la
    1.68
    Sekarang
    1.68
    Mereka
    1.66
    Противо
    1.64
    Добавлено
    1.63
    Activations Density 0.005%

    No Known Activations