© 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. 10-GEMMASCOPE-RES-131K
    7. 72185
    Prev
    Next
    INDEX
    Explanations

    object instantiation and method calls

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    writerow
    -1.12
    Condolences
    -1.11
     trong
    -1.09
    赑
    -1.08
     AKA
    -1.08
    Bulgaria
    -1.07
    Trayectoria
    -1.02
    cambrian
    -1.02
    naldo
    -1.02
     desactivar
    -1.01
    POSITIVE LOGITS
     such
    1.38
     then
    1.21
     karna
    1.09
     kemudian
    1.09
    дете
    1.09
     Übernach
    1.09
     based
    1.05
     teka
    1.05
     kark
    1.03
    ：
    1.02
    Activations Density 0.035%

    No Known Activations