© 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. 118859
    Prev
    Next
    INDEX
    Explanations

    financial numbers and eCommerce

    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
    ness
    -3.17
    an
    -2.67
    a
    -2.63
    觏
    -2.56
    ).
    -2.56
     voor
    -2.52
    ఙ
    -2.50
    訁
    -2.48
    1
    -2.44
    c
    -2.42
    POSITIVE LOGITS
    嗖
    2.73
    蕷
    2.69
     placés
    2.30
    鼙
    2.28
    奔驰
    2.28
     découver
    2.25
    rapeau
    2.20
     málo
    2.19
    ￫
    2.17
    籥
    2.16
    Activations Density 0.015%

    No Known Activations