© 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. 7051
    Prev
    Next
    INDEX
    Explanations

    modern-day

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ！"
    -1.92
    ですが
    -1.84
     espectaculares
    -1.81
     katk
    -1.80
     pembelian
    -1.80
    焢
    -1.77
     đị
    -1.77
     povezave
    -1.75
     uzyska
    -1.74
    充滿
    -1.73
    POSITIVE LOGITS
    “,
    2.28
    ↵↵
    2.20
     “
    1.95
     
    1.91
     acredita
    1.84
     podem
    1.76
    </th>
    1.75
      
    1.73
     It
    1.72
    乄
    1.71
    Activations Density 0.069%

    No Known Activations