© 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. 10-GEMMASCOPE-RES-131K
    4. 127319
    Prev
    Next
    INDEX
    Explanations

    equation of motion

    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
     culturale
    -1.45
     sinu
    -1.44
     epoca
    -1.39
    褙
    -1.38
     parati
    -1.38
     turco
    -1.34
    itize
    -1.33
     levis
    -1.33
     подоб
    -1.31
     plana
    -1.30
    POSITIVE LOGITS
     The
    1.63
     Every
    1.61
     for
    1.47
     a
    1.46
     in
    1.45
     Each
    1.45
     verbess
    1.41
     besonderes
    1.38
    之意
    1.35
     new
    1.34
    Activations Density 0.106%

    No Known Activations