© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    java.util.concurrent imports

    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
     gän
    -1.65
    瘣
    -1.63
    selbe
    -1.58
    ῞
    -1.55
     ursprünglich
    -1.51
    foundland
    -1.50
     totalement
    -1.50
    男人的
    -1.49
    是在
    -1.47
     ranting
    -1.47
    POSITIVE LOGITS
     this
    1.87
     from
    1.77
    </h2>
    1.73
    </h4>
    1.72
    葙
    1.59
     which
    1.57
     these
    1.51
     diesem
    1.48
     ikke
    1.47
     each
    1.41
    Activations Density 0.006%

    No Known Activations