© 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. 16613
    Prev
    Next
    INDEX
    Explanations

    salutations and addresses

    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
     Ländern
    -1.04
    Quieres
    -0.95
     conditions
    -0.94
     necesitaba
    -0.93
    Trichlor
    -0.93
    tığı
    -0.92
    Orléans
    -0.91
     basics
    -0.91
    źć
    -0.91
     sides
    -0.90
    POSITIVE LOGITS
    ！！！”
    1.10
    cestors
    1.08
     tungkol
    1.05
    нным
    1.04
    Dear
    1.02
    意味着
    1.02
     all
    1.02
     모두
    0.99
     NUEVO
    0.99
     пишет
    0.98
    Activations Density 0.022%

    No Known Activations