© 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. 30261
    Prev
    Next
    INDEX
    Explanations

    Egypt, Cairo, Bookmobile, BP, Al-Khalid

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cune
    -0.91
     malaysia
    -0.83
     Mesopotamia
    -0.80
     IRA
    -0.80
     Götter
    -0.79
    Кара
    -0.79
    {$\
    -0.78
    Бележки
    -0.77
     Dian
    -0.76
     Altar
    -0.74
    POSITIVE LOGITS
     Hy
    0.84
     Classifier
    0.74
    шую
    0.72
     demon
    0.71
     mastered
    0.69
     кух
    0.68
     mast
    0.68
     RESPONDENT
    0.67
    Hy
    0.66
    owm
    0.66
    Activations Density 0.019%

    No Known Activations