© 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. 84247
    Prev
    Next
    INDEX
    Explanations

    grief and bereavement

    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
    !
    -1.66
     if
    -1.59
    :
    -1.55
     =
    -1.54
     are
    -1.45
     /
    -1.39
    =
    -1.33
    .
    -1.30
    if
    -1.28
    ↵↵↵
    -1.27
    POSITIVE LOGITS
     fortaleza
    1.56
    Köszönöm
    1.34
     Belum
    1.34
    tamment
    1.32
     vokal
    1.32
    出来ました
    1.31
     Meksi
    1.27
     Bélgica
    1.27
     helicópter
    1.27
    bietet
    1.25
    Activations Density 0.035%

    No Known Activations