© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129202
    Prev
    Next
    INDEX
    Explanations

    multi-lingual and specific terms

    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
     that
    -1.50
     duong
    -1.45
    ↵↵↵
    -1.27
     („
    -1.21
     würden
    -1.19
     Affaires
    -1.18
    iamo
    -1.14
     nepiecieš
    -1.13
    tocks
    -1.13
    ofing
    -1.13
    POSITIVE LOGITS
     кількість
    1.42
    nora
    1.21
     обучение
    1.18
    bech
    1.18
    𝗩
    1.17
    Externí
    1.16
    служба
    1.15
     ответить
    1.14
    ˃
    1.13
     resulting
    1.12
    Activations Density 0.641%

    No Known Activations