© 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. 56899
    Prev
    Next
    INDEX
    Explanations

    song titles and performers

    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
     liters
    -0.87
    sira
    -0.83
     kirch
    -0.82
     regula
    -0.81
    ∊
    -0.79
    ⬍
    -0.79
    tham
    -0.78
    鍬
    -0.78
     linux
    -0.78
     Colomb
    -0.78
    POSITIVE LOGITS
     fröh
    0.83
    Страна
    0.81
     Jurí
    0.78
     Dion
    0.77
    Contours
    0.76
    窈
    0.76
     samot
    0.76
     instrumental
    0.76
     सेमी
    0.76
     ordinal
    0.75
    Activations Density 0.047%

    No Known Activations