© 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. 34-GEMMASCOPE-RES-131K
    7. 115486
    Prev
    Next
    INDEX
    Explanations

    metadata fields

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric tokens (numbers or digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     authors
    -1.53
    作者
    -1.24
    Authors
    -1.18
     作者
    -1.02
     authored
    -0.99
    AUTHOR
    -0.96
    Автор
    -0.96
    AUTHORS
    -0.94
     Authors
    -0.94
    authors
    -0.93
    POSITIVE LOGITS
     инжен
    0.77
     dotted
    0.75
     date
    0.75
    daya
    0.75
     golongan
    0.74
    ıyla
    0.72
    institutions
    0.70
     mobilya
    0.70
    uffy
    0.69
     kağıdı
    0.69
    Activations Density 0.152%

    No Known Activations