© 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. 40059
    Prev
    Next
    INDEX
    Explanations

    JSON/HTML structure keys and values

    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
     奶
    -1.06
     Jika
    -1.05
     düğün
    -0.99
    documentclass
    -0.98
    ditionally
    -0.95
     词
    -0.91
    bundes
    -0.90
    ˈ
    -0.90
    jika
    -0.90
    quarelle
    -0.89
    POSITIVE LOGITS
     iniziato
    0.93
     scoperto
    0.91
    ΡΟ
    0.90
     utilizó
    0.90
    駅前
    0.89
     vorhandenen
    0.88
    oubted
    0.88
     mentioned
    0.88
     rimanere
    0.88
    ائص
    0.87
    Activations Density 0.003%

    No Known Activations