© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60290
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     岁
    -1.27
     们
    -1.25
     
    -1.23
    twenty
    -1.17
     场
    -1.13
    mathrm
    -1.09
    视着
    -1.08
    　　……
    -1.06
    nearly
    -1.05
     Kontexten
    -1.05
    POSITIVE LOGITS
     
    1.70
     veck
    1.29
     säs
    0.99
    先は
    0.98
     snabb
    0.97
     kunt
    0.95
     kvä
    0.93
     blessure
    0.92
    ʕ
    0.91
     blessures
    0.91
    Activations Density 0.270%

    No Known Activations