© 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. 3592
    Prev
    Next
    INDEX
    Explanations

    official adviser spokesperson aide

    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
    されます
    -0.77
     concierge
    -0.77
    
    -0.76
     visar
    -0.74
    辈子
    -0.72
    慨
    -0.72
    Masters
    -0.71
    pdo
    -0.70
     pounding
    -0.68
    玩笑
    -0.67
    POSITIVE LOGITS
     matters
    1.10
     президента
    0.97
    बि
    0.85
    ├──
    0.84
    deas
    0.81
    omsday
    0.80
     medias
    0.79
    เรื่อง
    0.79
     Attached
    0.79
    стей
    0.77
    Activations Density 0.014%

    No Known Activations