© 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. 110889
    Prev
    Next
    INDEX
    Explanations

    code structure or prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    asterisks or list markers that begin a line or list item.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     of
    -1.84
    "
    -1.78
    後で
    -1.73
     —
    -1.69
     Again
    -1.68
     
    -1.58
     then
    -1.53
     Please
    -1.51
     You
    -1.48
    おすすめ
    -1.48
    POSITIVE LOGITS
    Ꮣ
    2.00
    縠
    1.95
    </i>
    1.80
    ਲ਼
    1.80
    
    1.73
     うさぎ
    1.69
    笤
    1.63
    旆
    1.63
    NDICE
    1.60
    珵
    1.60
    Activations Density 0.019%

    No Known Activations