© 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. 34-GEMMASCOPE-RES-131K
    7. 84769
    Prev
    Next
    INDEX
    Explanations

    perfect completion; full

    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_34/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
     semplice
    -0.82
     bark
    -0.73
    kø
    -0.72
    ponential
    -0.71
     способом
    -0.71
    もしれません
    -0.71
     trovo
    -0.71
     Kitz
    -0.70
    quettes
    -0.70
     Raton
    -0.70
    POSITIVE LOGITS
     کامل
    1.11
     perfect
    1.05
    perfect
    1.03
     Perfect
    1.00
    Perfect
    0.96
     full
    0.93
    ほぼ
    0.87
     parfaite
    0.84
     peł
    0.83
    full
    0.83
    Activations Density 0.108%

    No Known Activations