© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    enjoyable activities and pastimes

    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
    illam
    -0.85
    ības
    -0.80
     収納
    -0.79
     viva
    -0.77
    haul
    -0.77
    oglio
    -0.77
    cké
    -0.77
    ила
    -0.75
    islative
    -0.75
    ुप
    -0.74
    POSITIVE LOGITS
     activities
    4.97
     activity
    4.44
    activities
    3.64
    Activities
    3.56
     Activities
    3.45
     actividades
    3.39
    activity
    3.16
     ACTIVITIES
    3.06
    活動
    2.91
    活动
    2.88
    Activations Density 0.091%

    No Known Activations