© 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. 79831
    Prev
    Next
    INDEX
    Explanations

    Nick Clegg

    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
    متن
    -1.06
     QtCore
    -1.01
     podían
    -1.00
    ଶ
    -0.98
     tenían
    -0.96
     hacían
    -0.95
    //}
    -0.95
    ꧂
    -0.94
     Ayrıca
    -0.94
     habían
    -0.94
    POSITIVE LOGITS
    在这种
    1.00
     îi
    0.94
    autres
    0.89
     непосредственно
    0.88
    ews
    0.88
     parete
    0.87
     firs
    0.87
    i
    0.86
     other
    0.86
     живет
    0.86
    Activations Density 0.000%

    No Known Activations