© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11061
    Prev
    Next
    INDEX
    Explanations

    you need or want

    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
     of
    -1.05
     to
    -0.97
     Татьяна
    -0.94
    旖
    -0.94
     yet
    -0.93
     Арме
    -0.91
     STRUCTURE
    -0.90
     Наталья
    -0.90
     but
    -0.88
    Loving
    -0.88
    POSITIVE LOGITS
     needed
    1.47
     appropriate
    1.23
     necessary
    1.15
     действительно
    1.14
     those
    1.14
    
    
    1.10
    而不是
    1.09
     what
    1.06
    needed
    1.06
     eerst
    1.05
    Activations Density 0.037%

    No Known Activations