© 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. 22-GEMMASCOPE-RES-131K
    7. 95769
    Prev
    Next
    INDEX
    Explanations

    prominence and importance

    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_22/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
    Ứng
    -1.09
    ṉ
    -1.02
    Să
    -0.95
    कृति
    -0.91
     slippery
    -0.90
    అ
    -0.90
    اقرأ
    -0.88
    Scrollbar
    -0.88
     treball
    -0.88
    레이
    -0.87
    POSITIVE LOGITS
     important
    1.46
     importance
    1.33
     movers
    1.23
     dominant
    1.21
    importance
    1.15
     dominance
    1.10
     superiority
    1.09
     importancia
    1.09
     superior
    1.07
    important
    1.06
    Activations Density 0.050%

    No Known Activations