© 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. 30026
    Prev
    Next
    INDEX
    Explanations

    collections of data or space

    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
    亮点
    -0.82
    ございました
    -0.80
     calories
    -0.80
    Palace
    -0.79
    Mismatch
    -0.78
     suyo
    -0.77
    Encontra
    -0.76
    ñones
    -0.76
     nucleotides
    -0.75
    decade
    -0.75
    POSITIVE LOGITS
     dataset
    1.67
     database
    1.36
     population
    1.21
     universe
    1.09
     전체
    1.07
     input
    1.05
    dataSet
    1.05
     collection
    1.05
    数据集
    1.02
    DataSet
    1.00
    Activations Density 0.175%

    No Known Activations