© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106363
    Prev
    Next
    INDEX
    Explanations

    years old or of age

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     روح
    -1.08
     soul
    -0.93
    soul
    -0.90
    tissima
    -0.82
    bosity
    -0.81
     sô
    -0.78
    filtration
    -0.77
     sensibly
    -0.75
    ųjų
    -0.74
    갈
    -0.74
    POSITIVE LOGITS
     old
    2.72
     of
    1.73
    old
    1.59
     age
    1.54
     olds
    1.52
     older
    1.42
     ago
    1.31
     vieux
    1.26
    老
    1.23
     idade
    1.14
    Activations Density 0.031%

    No Known Activations