© 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. 3488
    Prev
    Next
    INDEX
    Explanations

    effect on outcomes

    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
    因为它
    -1.28
    有個
    -1.23
    矇
    -1.21
     вашего
    -1.13
    还有一个
    -1.11
    有一個
    -1.11
    的在
    -1.10
    一根
    -1.08
     diesmal
    -1.07
    マキ
    -1.07
    POSITIVE LOGITS
     the
    4.22
     both
    1.93
     their
    1.65
     our
    1.62
     how
    1.42
     både
    1.39
     overall
    1.39
    หรือ
    1.35
     parfü
    1.33
     or
    1.30
    Activations Density 0.120%

    No Known Activations