© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129372
    Prev
    Next
    INDEX
    Explanations

    aid in or assist in

    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
     [
    -2.05
     *
    -1.99
    也不是
    -1.66
     Of
    -1.59
     
    -1.56
     /
    -1.54
     -
    -1.52
     {
    -1.49
    iri
    -1.48
    Of
    -1.48
    POSITIVE LOGITS
    
    1.88
    柺
    1.72
    voer
    1.69
     nadru
    1.66
     that
    1.59
     kwar
    1.55
    鱂
    1.52
    嫫
    1.52
    銫
    1.50
    咘
    1.48
    Activations Density 0.007%

    No Known Activations