© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21057
    Prev
    Next
    INDEX
    Explanations

    junctions, nodes, and origins

    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
     ۱۵
    -1.52
     ۷
    -1.50
     unbelievably
    -1.45
     ۱۰
    -1.44
    켭
    -1.41
     ۱۶
    -1.39
     AMAZING
    -1.38
     entire
    -1.38
     ۱۱
    -1.38
     amazing
    -1.37
    POSITIVE LOGITS
    صبح
    1.45
    內容簡介
    1.40
     escondido
    1.33
     nestled
    1.32
     identificado
    1.32
     with
    1.30
    Lynx
    1.30
     representado
    1.29
     Treatments
    1.25
    Lá
    1.24
    Activations Density 0.197%

    No Known Activations