© 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. 28969
    Prev
    Next
    INDEX
    Explanations

    html table tbody

    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
            
    -2.28
     {
    -1.99
    <sup>
    -1.80
     has
    -1.75
                             
    -1.70
    6
    -1.68
     {
    -1.68
     但是
    -1.64
     ‘
    -1.63
     summed
    -1.60
    POSITIVE LOGITS
    <bos>
    2.38
    この時期
    1.77
    デメリット
    1.76
     flyg
    1.74
    replyreport
    1.70
    媖
    1.69
    嗶
    1.66
    この日
    1.64
    tbody
    1.61
    Причины
    1.60
    Activations Density 0.008%

    No Known Activations