© 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. 65391
    Prev
    Next
    INDEX
    Explanations

    years and authors

    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
    ígenes
    -1.55
     célula
    -1.52
     résine
    -1.52
    ֗
    -1.47
    
    -1.41
     atracción
    -1.38
     також
    -1.38
    chnet
    -1.36
     elegancia
    -1.36
     pureza
    -1.33
    POSITIVE LOGITS
     in
    1.42
     except
    1.35
    b
    1.31
     Its
    1.31
     Except
    1.30
     types
    1.30
     ofrecen
    1.29
    w
    1.29
    m
    1.29
     Their
    1.28
    Activations Density 0.013%

    No Known Activations