© 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. 127266
    Prev
    Next
    INDEX
    Explanations

    officials said or directed

    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
    Semitic
    -1.96
    联网
    -1.95
    issionais
    -1.79
    ebab
    -1.77
     巷
    -1.70
    贋
    -1.63
     diversified
    -1.62
    tım
    -1.58
    Semitism
    -1.56
    🪆
    -1.55
    POSITIVE LOGITS
     of
    2.16
    
    1.98
    ⚋
    1.94
     メニュー
    1.88
    スポンサーリンク
    1.87
     هذا
    1.84
    垍
    1.84
    部分が
    1.80
     одному
    1.79
    5
    1.75
    Activations Density 0.004%

    No Known Activations