© 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. 3498
    Prev
    Next
    INDEX
    Explanations

    postal addresses

    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
    pyrid
    -0.75
    날
    -0.73
     sınıf
    -0.68
     Fifth
    -0.67
     Dynamics
    -0.66
    colin
    -0.66
    ObjectModel
    -0.65
    通販
    -0.65
     Mandel
    -0.65
    öhne
    -0.65
    POSITIVE LOGITS
     daug
    0.74
     nepo
    0.68
    deau
    0.67
    Перевод
    0.67
    рби
    0.66
     Fortnite
    0.65
    KeyStore
    0.64
     prost
    0.63
     井
    0.63
    ждународ
    0.62
    Activations Density 0.053%

    No Known Activations