© 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. 62414
    Prev
    Next
    INDEX
    Explanations

    studio album

    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
    utare
    -0.79
     ış
    -0.75
    外線
    -0.74
    benz
    -0.74
    inetti
    -0.72
    :{
    -0.71
     نویس
    -0.70
     beitragen
    -0.69
    ayam
    -0.67
     amateurs
    -0.66
    POSITIVE LOGITS
     album
    5.44
     albums
    4.22
    album
    3.75
     альбо
    3.34
    Album
    3.31
     Album
    3.17
    アルバム
    3.11
     álbum
    3.03
    albums
    3.02
     ALBUM
    2.84
    Activations Density 0.151%

    No Known Activations