© 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. 36033
    Prev
    Next
    INDEX
    Explanations

    recommendations and encouragements

    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
     my
    -1.28
     lorsqu
    -1.18
     passat
    -1.00
    dahl
    -0.98
     הַ
    -0.98
    éticas
    -0.96
    Слайд
    -0.94
     untersch
    -0.94
     dział
    -0.94
     graag
    -0.93
    POSITIVE LOGITS
    mathrm
    1.28
     yourselves
    1.27
     yourself
    1.27
     either
    1.26
     menghindari
    1.19
    炒め
    1.13
     already
    1.09
    已经
    1.09
     nhung
    1.07
    
    1.07
    Activations Density 0.074%

    No Known Activations