© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    as, as a, x as y, as x, as, x as, x as y, as, as x

    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
     that
    -0.94
     antemano
    -0.85
     Szene
    -0.79
     supuestamente
    -0.79
    ありません
    -0.79
    based
    -0.78
     either
    -0.76
     based
    -0.75
     llegamos
    -0.74
    Hanya
    -0.72
    POSITIVE LOGITS
    として
    3.34
     olarak
    3.00
     as
    2.77
    ként
    2.56
    としての
    2.00
     として
    1.80
    로
    1.66
    である
    1.62
    としては
    1.62
    으로
    1.59
    Activations Density 0.004%

    No Known Activations