© 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. 105812
    Prev
    Next
    INDEX
    Explanations

    website links and sources

    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
     Subsequently
    -1.66
     It
    -1.66
     There
    -1.63
    ซึ่ง
    -1.51
     from
    -1.51
    儼
    -1.50
    Также
    -1.48
     Therefore
    -1.46
     Ultimately
    -1.46
     Interestingly
    -1.45
    POSITIVE LOGITS
     onsdag
    1.67
    .~(\
    1.66
     mentales
    1.65
     torsdag
    1.64
     uten
    1.63
    もしれない
    1.62
     fordi
    1.61
     lørdag
    1.60
    ithe
    1.59
     последнее
    1.54
    Activations Density 0.562%

    No Known Activations