© 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. 22-GEMMASCOPE-RES-131K
    7. 13413
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming keywords

    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_22/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
    
    -0.82
     publicó
    -0.77
     meninos
    -0.73
    kilometer
    -0.73
    kunta
    -0.71
     baratas
    -0.71
    ຼ
    -0.71
     način
    -0.71
    tillo
    -0.70
    itação
    -0.70
    POSITIVE LOGITS
     dizaine
    0.77
     Shor
    0.77
    コンセプト
    0.76
     fenêtre
    0.75
    üsü
    0.74
    رأة
    0.74
    ここでは
    0.74
     طی
    0.74
    Parece
    0.73
    lateinit
    0.73
    Activations Density 0.037%

    No Known Activations