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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34925
    Prev
    Next
    INDEX
    Explanations

    defining current insufficiencies

    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
    Dès
    -0.89
    ahan
    -0.89
    上有
    -0.86
    Lepid
    -0.85
    esis
    -0.84
     другим
    -0.81
    шими
    -0.80
    昙
    -0.79
    roskop
    -0.79
     doubles
    -0.78
    POSITIVE LOGITS
    只
    1.16
    currently
    1.08
    Lack
    1.06
     existing
    1.05
     currently
    1.05
     lack
    1.04
    がありません
    1.03
     actuellement
    1.03
     insufficient
    1.00
     thiếu
    0.99
    Activations Density 0.173%

    No Known Activations