© 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. 278
    Prev
    Next
    INDEX
    Explanations

    object comparison and duplication methods

    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
    絝
    -1.87
     entrenamiento
    -1.80
    
    -1.77
    矬
    -1.77
    袛
    -1.75
     pierws
    -1.74
    媪
    -1.73
    蓠
    -1.72
    
    -1.72
     mamy
    -1.70
    POSITIVE LOGITS
    '
    2.28
    8
    2.14
    2
    2.13
     for
    1.82
    3
    1.80
    1
    1.79
    4
    1.75
    7
    1.73
    when
    1.73
    6
    1.66
    Activations Density 0.005%

    No Known Activations