© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    past participles used in states or completion

    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
     wzglę
    -1.73
    閦
    -1.66
    摀
    -1.66
     możliwe
    -1.65
     śmierci
    -1.65
    唿
    -1.65
     plazos
    -1.57
     gwaran
    -1.55
     aksesuar
    -1.55
     montaż
    -1.53
    POSITIVE LOGITS
     with
    1.78
     and
    1.77
     for
    1.64
      
    1.38
     would
    1.34
    より
    1.28
    In
    1.26
    餃子
    1.23
     satunya
    1.22
    踵
    1.22
    Activations Density 0.035%

    No Known Activations