© 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. 32756
    Prev
    Next
    INDEX
    Explanations

    reduced to essentials, scale, or simple terms

    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
     of
    -1.29
     ஏ
    -1.02
    遑
    -1.00
    ebenarnya
    -0.99
     great
    -0.96
     Kriege
    -0.96
    rawdź
    -0.94
    лно
    -0.91
    痊
    -0.91
     numberWith
    -0.89
    POSITIVE LOGITS
     to
    1.70
    ↵
    1.36
     Reduce
    1.12
     reinen
    1.05
     into
    1.04
    WaitFor
    1.03
     simply
    1.02
    reduced
    1.02
     REDUC
    1.01
     reduz
    1.00
    Activations Density 0.028%

    No Known Activations