© 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. 34-GEMMASCOPE-RES-131K
    7. 82463
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems and results

    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_34/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
    解釋
    -0.90
     definition
    -0.90
     Merriam
    -0.89
    definition
    -0.77
    定义
    -0.76
     пример
    -0.74
     example
    -0.73
     Верхов
    -0.73
     الشمس
    -0.72
    解释
    -0.72
    POSITIVE LOGITS
     proved
    1.82
    proved
    1.68
     stated
    1.67
    statement
    1.48
     statement
    1.48
    Statement
    1.47
     proven
    1.47
    stated
    1.43
     stating
    1.42
     statements
    1.40
    Activations Density 0.076%

    No Known Activations