© 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. 72772
    Prev
    Next
    INDEX
    Explanations

    semiconductor device

    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
     more
    -1.79
     
    -1.70
    quilo
    -1.50
    ׇ
    -1.48
    
    -1.42
     exceptionnel
    -1.41
    ":"+
    -1.38
    "+
    -1.35
     RISERV
    -1.30
    >"+
    -1.30
    POSITIVE LOGITS
    太过
    1.67
     illustratie
    1.66
    וּ
    1.62
    ଵ
    1.60
     слишком
    1.59
    ৫
    1.58
     habrían
    1.52
    ּוֹ
    1.51
    太大
    1.47
    還好
    1.45
    Activations Density 0.169%

    No Known Activations