© 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. 80913
    Prev
    Next
    INDEX
    Explanations

    code declarations and structures

    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
     الأس
    -0.85
    ｢
    -0.75
     комнат
    -0.71
    ovem
    -0.71
    runOnUiThread
    -0.70
     появление
    -0.70
    StateToProps
    -0.68
    ConfigService
    -0.68
     خودش
    -0.67
    郝
    -0.65
    POSITIVE LOGITS
    oane
    0.99
    Anak
    0.89
     itemView
    0.89
     республи
    0.88
    ftime
    0.86
    occasione
    0.83
     winters
    0.82
    holdings
    0.82
     views
    0.81
     там
    0.81
    Activations Density 0.001%

    No Known Activations