© 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. 10-GEMMASCOPE-RES-131K
    7. 86851
    Prev
    Next
    INDEX
    Explanations

    struggle, struggling, struggles

    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
    羮
    -1.65
     premiere
    -1.65
    The
    -1.63
    盌
    -1.56
     piac
    -1.54
     ´
    -1.52
     作り方
    -1.52
     한국
    -1.51
     لیتر
    -1.50
     детей
    -1.49
    POSITIVE LOGITS
    rinology
    1.70
    而
    1.66
    ти
    1.65
     citada
    1.56
    飚
    1.54
     habrían
    1.52
    ctions
    1.52
     coś
    1.52
    bosis
    1.51
     навыки
    1.50
    Activations Density 0.013%

    No Known Activations