© 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. 47230
    Prev
    Next
    INDEX
    Explanations

    shared libraries and DLLs

    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
    IRQn
    -0.82
     سنتی
    -0.78
    ルーム
    -0.76
    WaitGroup
    -0.73
    талья
    -0.73
     maize
    -0.72
     ترکی
    -0.72
     kasarigan
    -0.72
    颚
    -0.72
    虚拟
    -0.69
    POSITIVE LOGITS
     DLL
    2.02
     library
    1.98
     lib
    1.71
     dll
    1.67
    lib
    1.59
     libraries
    1.51
    DLL
    1.49
     libs
    1.45
     libr
    1.45
    dll
    1.44
    Activations Density 0.144%

    No Known Activations