© 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. 19144
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax

    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
     oportunidades
    -1.63
    Welche
    -1.45
     the
    -1.45
     hundred
    -1.45
    娘娘
    -1.43
     jsou
    -1.43
    Jetzt
    -1.34
     anderen
    -1.34
     preparados
    -1.33
    スコット
    -1.33
    POSITIVE LOGITS
    1
    1.74
    0
    1.57
     again
    1.48
    3
    1.47
     sekal
    1.35
     In
    1.34
     تمامی
    1.32
    4
    1.29
    ="";
    1.29
     "";
    1.28
    Activations Density 0.122%

    No Known Activations