© 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. 10-GEMMASCOPE-RES-131K
    7. 42724
    Prev
    Next
    INDEX
    Explanations

    abstract class definitions

    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_10/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
    嵛
    -1.68
     würden
    -1.66
     The
    -1.66
     alcune
    -1.55
     furent
    -1.51
     alcuni
    -1.50
     trouvent
    -1.49
    なども
    -1.49
     применять
    -1.48
    莇
    -1.48
    POSITIVE LOGITS
     that
    1.66
    For
    1.63
    In
    1.54
    To
    1.50
    ↵
    1.47
    By
    1.46
     kiş
    1.43
    Before
    1.41
    His
    1.41
     sanitaria
    1.39
    Activations Density 0.030%

    No Known Activations