© 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. 9720
    Prev
    Next
    INDEX
    Explanations

    crater, grating, creatine

    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
     ſie
    -2.64
    蜑
    -2.55
    獃
    -2.50
     titolata
    -2.47
    Ꭳ
    -2.47
    我们
    -2.41
    都沒
    -2.39
    锜
    -2.34
    鹚
    -2.33
     不锈钢
    -2.31
    POSITIVE LOGITS
    除此之外
    2.27
     otras
    2.20
     similares
    2.09
    而在
    2.03
     
    1.97
     gul
    1.95
    与此同时
    1.95
    但他
    1.94
    зап
    1.94
    ：
    1.93
    Activations Density 0.003%

    No Known Activations