© 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. 86578
    Prev
    Next
    INDEX
    Explanations

    believe me or believe that

    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
     bardzo
    -1.61
    哙
    -1.46
    ią
    -1.39
     nejen
    -1.39
     และ
    -1.38
     precisely
    -1.37
     Размер
    -1.35
    我好
    -1.31
     importantly
    -1.30
     Moreover
    -1.30
    POSITIVE LOGITS
     <>",
    1.46
    телей
    1.38
     هستیم
    1.37
    优秀的
    1.37
    所有的
    1.36
    sistence
    1.34
    我們的
    1.34
     мы
    1.30
    的所有
    1.29
    </strong>
    1.27
    Activations Density 0.007%

    No Known Activations