© 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. 47198
    Prev
    Next
    INDEX
    Explanations

    geographical locations and legal filings

    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
    cot
    -0.73
    🐳
    -0.73
    CRIP
    -0.73
     запре
    -0.73
    奇迹
    -0.72
     Dunk
    -0.72
    多少钱
    -0.70
    还想
    -0.70
    formatie
    -0.69
    すぎた
    -0.69
    POSITIVE LOGITS
     Sioux
    1.21
    multiplier
    0.77
    倡
    0.77
     fény
    0.77
     Demp
    0.74
     sikker
    0.70
     Mohr
    0.70
     remote
    0.70
     Trier
    0.69
    forhold
    0.69
    Activations Density 0.014%

    No Known Activations