© 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. 123937
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating 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
     or
    -2.00
     any
    -1.80
     by
    -1.72
     '
    -1.64
    bolsa
    -1.63
     from
    -1.62
    quần
    -1.58
     damaligen
    -1.56
     which
    -1.52
     Because
    -1.52
    POSITIVE LOGITS
     telah
    1.64
    recently
    1.63
     depuis
    1.57
    骉
    1.57
     zet
    1.52
     έχει
    1.51
     anteriormente
    1.48
    upto
    1.46
    already
    1.45
    힉
    1.45
    Activations Density 0.197%

    No Known Activations