© 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. 22-GEMMASCOPE-RES-131K
    7. 64463
    Prev
    Next
    INDEX
    Explanations

    while or pending action

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     today
    -0.99
     successo
    -0.89
     martens
    -0.87
     heutige
    -0.87
     選択
    -0.86
     Sudah
    -0.85
     Aktivität
    -0.82
    pēc
    -0.81
     with
    -0.79
     seid
    -0.79
    POSITIVE LOGITS
    await
    1.27
     await
    1.23
     awaiting
    1.15
     menunggu
    0.99
     wait
    0.97
     until
    0.97
     waiting
    0.92
    waiting
    0.92
    until
    0.91
     investigation
    0.90
    Activations Density 0.029%

    No Known Activations