© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119148
    Prev
    Next
    INDEX
    Explanations

    most or least

    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
    Not in Any Lists

    No Comments

    Negative Logits
    randir
    -0.95
    zieć
    -0.91
    游戏介绍
    -0.91
    ())))
    -0.90
    тко
    -0.90
    isantes
    -0.88
     lehe
    -0.88
     même
    -0.88
    🉐
    -0.88
     pluie
    -0.87
    POSITIVE LOGITS
     most
    5.31
     가장
    3.94
     наиболее
    3.75
     найбіль
    3.72
    最も
    3.72
     सबसे
    3.70
    最
    3.56
     najbardziej
    3.55
    が一番
    3.28
     greatest
    3.16
    Activations Density 0.227%

    No Known Activations