© 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. 106210
    Prev
    Next
    INDEX
    Explanations

    logarithmic scales or transformations

    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
    reado
    -0.74
    སྐ
    -0.69
    statistic
    -0.67
    seled
    -0.66
     gelijk
    -0.66
     Postal
    -0.66
    Mour
    -0.66
    Sexual
    -0.66
     мара
    -0.65
    assin
    -0.65
    POSITIVE LOGITS
     logarithmic
    3.55
     log
    3.50
    log
    3.27
     Log
    3.13
    Log
    3.02
     LOG
    2.61
     logs
    2.59
     logarith
    2.55
    LOG
    2.52
     logar
    2.39
    Activations Density 0.028%

    No Known Activations