© 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. 123798
    Prev
    Next
    INDEX
    Explanations

    clay, brick, tile, building materials

    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
     schuhe
    -1.46
     actually
    -1.46
    ’
    -1.40
     you
    -1.35
    Их
    -1.31
     didn
    -1.31
    ässig
    -1.28
    f
    -1.23
    遊んで
    -1.23
     iglesias
    -1.23
    POSITIVE LOGITS
     betreffenden
    1.36
     verheir
    1.27
    lemme
    1.24
     Kondisi
    1.23
    țiune
    1.23
    है
    1.20
     vielfach
    1.17
     papà
    1.17
     prossimo
    1.16
    apri
    1.16
    Activations Density 0.036%

    No Known Activations