© 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. 105106
    Prev
    Next
    INDEX
    Explanations

    I think

    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
    ↵
    -2.14
     of
    -1.74
    if
    -1.66
    r
    -1.57
     their
    -1.55
    ,”
    -1.51
     погиб
    -1.47
     each
    -1.46
     và
    -1.43
    s
    -1.42
    POSITIVE LOGITS
     Finally
    1.61
     tujuh
    1.59
     desglose
    1.59
     graciosas
    1.50
     contaba
    1.49
     póster
    1.48
     poetas
    1.45
     conceptos
    1.45
     рекомендуется
    1.45
     ofreció
    1.43
    Activations Density 0.040%

    No Known Activations