© 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. 106281
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    sepeda
    -0.77
    unción
    -0.76
     mahasiswa
    -0.71
     проводить
    -0.70
    enseignements
    -0.69
     CITED
    -0.69
    waitKey
    -0.69
    ToAction
    -0.69
     лек
    -0.68
    wanych
    -0.68
    POSITIVE LOGITS
     hope
    0.94
     HOPE
    0.89
     Classe
    0.89
    Istorija
    0.87
     extremely
    0.84
     Question
    0.82
    Question
    0.82
    TERY
    0.81
     künstler
    0.80
     attempt
    0.79
    Activations Density 0.006%

    No Known Activations