© 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. 104337
    Prev
    Next
    INDEX
    Explanations

    cost of living and price changes

    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
     که
    -1.66
    。
    -1.64
    as
    -1.55
    >
    -1.54
    mingen
    -1.54
     que
    -1.50
    ERS
    -1.46
     ‘
    -1.46
    loride
    -1.41
    这是一
    -1.40
    POSITIVE LOGITS
     conferir
    1.93
     vorige
    1.70
     esperamos
    1.55
     contribuir
    1.52
     impedir
    1.52
     comunicar
    1.51
    лася
    1.46
    ve
    1.46
     podríamos
    1.46
    arım
    1.44
    Activations Density 0.007%

    No Known Activations