© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90359
    Prev
    Next
    INDEX
    Explanations

    `ET AL` or `and `

    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
     både
    -3.22
     They
    -2.55
     ò
    -2.39
    ofthe
    -2.36
     zarówno
    -2.23
    RICIA
    -2.23
    ophageal
    -2.22
    ofa
    -2.20
     også
    -2.19
    饽
    -2.17
    POSITIVE LOGITS
    \
    2.91
    This
    2.64
    行
    2.45
     *
    2.44
        
    2.33
     then
    2.31
     sebagainya
    2.30
     خواهد
    2.28
     frankly
    2.27
     presumed
    2.25
    Activations Density 0.005%

    No Known Activations