© 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. 65481
    Prev
    Next
    INDEX
    Explanations

    definitions of words

    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
     одну
    -2.08
    ｲ
    -1.90
     manguera
    -1.78
    鈊
    -1.70
    𓐍
    -1.68
    蒾
    -1.65
     juc
    -1.63
    RE
    -1.63
     belles
    -1.60
     penurunan
    -1.60
    POSITIVE LOGITS
    ⇴
    1.66
    ，「
    1.64
     escrita
    1.64
     kemudian
    1.63
     überras
    1.54
     lược
    1.54
     高級
    1.52
    ключение
    1.50
     apprehensive
    1.50
    常常
    1.48
    Activations Density 0.034%

    No Known Activations