© 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. 10-GEMMASCOPE-RES-131K
    7. 72766
    Prev
    Next
    INDEX
    Explanations

    words starting with Cro

    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
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -3.13
    \
    -2.78
    苼
    -2.48
    轳
    -2.42
    ↵↵
    -2.33
      
    -2.28
    辔
    -2.23
    你会
    -2.19
     verschied
    -2.17
     complet
    -2.17
    POSITIVE LOGITS
    ised
    2.36
    azione
    2.33
    er
    2.33
    i
    2.27
    馀
    2.25
    able
    2.23
    頔
    2.23
    waniu
    2.22
    èses
    2.22
     unusually
    2.22
    Activations Density 0.007%

    No Known Activations