© 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. 130391
    Prev
    Next
    INDEX
    Explanations

    graphic design or graphic novels

    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
    ка
    -2.38
    翾
    -2.14
     thinks
    -1.79
    Cómo
    -1.78
     With
    -1.78
    when
    -1.77
    亟
    -1.74
    モード
    -1.73
    at
    -1.73
     be
    -1.73
    POSITIVE LOGITS
     individuellen
    2.25
     täglichen
    2.22
     și
    2.22
    
    2.17
    ляции
    2.14
     sicheren
    2.13
    และ
    2.13
     帅气
    2.11
     семье
    2.08
    ࿆
    2.05
    Activations Density 0.031%

    No Known Activations