© 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. 10-GEMMASCOPE-RES-131K
    7. 6813
    Prev
    Next
    INDEX
    Explanations

    average and normal

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     două
    -1.94
    的两
    -1.86
     blauwe
    -1.85
    为例
    -1.85
    龅
    -1.81
    鲣
    -1.80
     unieke
    -1.78
    鳙
    -1.76
    {
    -1.75
     évé
    -1.73
    POSITIVE LOGITS
    この
    1.97
    This
    1.90
     of
    1.78
    )
    1.65
    raient
    1.60
    5
    1.58
    新型
    1.58
    “
    1.52
     simile
    1.51
    "
    1.48
    Activations Density 0.004%

    No Known Activations