© 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. 71434
    Prev
    Next
    INDEX
    Explanations

    class property declarations and relationships

    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
    lampen
    -1.04
    Приятного
    -0.98
    isissez
    -0.98
    voorbeeld
    -0.96
     Franse
    -0.95
    𝐖
    -0.95
    ฿
    -0.95
     meub
    -0.94
    îtres
    -0.93
     véhic
    -0.93
    POSITIVE LOGITS
     assigned
    1.05
     parent
    1.02
     supporting
    0.98
     belong
    0.97
     więks
    0.96
     connect
    0.96
     creada
    0.94
     relation
    0.94
     connects
    0.92
     parents
    0.91
    Activations Density 0.006%

    No Known Activations