© 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. 118492
    Prev
    Next
    INDEX
    Explanations

    examples and demonstrations

    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
     капю
    -0.98
    Neces
    -0.85
    亚马逊
    -0.85
    esso
    -0.80
     snippetHide
    -0.80
    ኃ
    -0.79
    Помо
    -0.77
    contexts
    -0.77
    ђе
    -0.76
    ACCIÓN
    -0.76
    POSITIVE LOGITS
     demonstration
    1.26
     Demonstration
    1.08
     demonstrations
    1.01
    vings
    0.96
     example
    0.95
    Demonstration
    0.89
     Demo
    0.87
    演示
    0.86
    demo
    0.84
    Example
    0.82
    Activations Density 0.037%

    No Known Activations