© 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. 836
    Prev
    Next
    INDEX
    Explanations

    loss of life and jobs

    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
     fichiers
    -1.64
     valla
    -1.62
     indeb
    -1.51
     latina
    -1.48
     espr
    -1.47
     luxem
    -1.45
     kili
    -1.45
    
    -1.45
     alip
    -1.44
     summari
    -1.42
    POSITIVE LOGITS
     to
    1.88
     in
    1.49
    についても
    1.48
     Дне
    1.44
     way
    1.40
    旸
    1.40
     čet
    1.39
     asamblea
    1.39
     проектов
    1.39
     muere
    1.39
    Activations Density 0.010%

    No Known Activations