© 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. 62488
    Prev
    Next
    INDEX
    Explanations

    is or is not the case

    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
     Ceres
    -0.84
    的所有
    -0.84
    Caching
    -0.83
    Ой
    -0.82
     lumea
    -0.82
    Ⴀ
    -0.82
    productList
    -0.82
     sw
    -0.82
    резать
    -0.82
    chaqueta
    -0.81
    POSITIVE LOGITS
     case
    3.11
     the
    2.81
    case
    2.00
     cases
    1.86
     случае
    1.75
     tilf
    1.72
     caso
    1.70
    Case
    1.59
     경우
    1.50
     przypadku
    1.48
    Activations Density 0.032%

    No Known Activations