© 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. 30001
    Prev
    Next
    INDEX
    Explanations

    Russian names and words

    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
     nothing
    -0.88
     vaikka
    -0.85
    ónimo
    -0.71
     ['',
    -0.69
     处理
    -0.69
    ඒ
    -0.68
    NameIn
    -0.66
    འད
    -0.65
    aints
    -0.65
     няма
    -0.65
    POSITIVE LOGITS
     cuartos
    0.79
    Dru
    0.73
    镝
    0.71
     crucero
    0.71
     Gó
    0.70
     vse
    0.69
    xxxxx
    0.69
     sequential
    0.69
     virkelig
    0.69
    Collective
    0.68
    Activations Density 0.029%

    No Known Activations