© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15449
    Prev
    Next
    INDEX
    Explanations

    refilling, reflow, refolding

    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
    -
    -2.64
    }$
    -2.45
    ⸫
    -2.41
     him
    -2.38
    
    -2.36
    {
    -2.30
    '
    -2.27
    1
    -2.23
    ta
    -2.23
     are
    -2.20
    POSITIVE LOGITS
    捽
    2.50
    也
    2.38
    メリカ
    2.36
     Mereka
    2.30
    罨
    2.17
     火鍋
    2.13
    ！"
    2.08
    СЯ
    2.06
    ၜ
    2.06
    
    2.00
    Activations Density 0.002%

    No Known Activations