© 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. 75675
    Prev
    Next
    INDEX
    Explanations

    common theme, factor, or denominator

    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
     A
    -1.97
     While
    -1.74
         
    -1.72
     Because
    -1.71
     Perhaps
    -1.64
    ;
    -1.64
     Some
    -1.63
     If
    -1.61
     Unfortunately
    -1.55
     Actually
    -1.54
    POSITIVE LOGITS
     throughout
    1.81
     platí
    1.63
    seende
    1.62
     mají
    1.59
     exti
    1.58
     maint
    1.57
    たびに
    1.54
     medlems
    1.51
     picioare
    1.50
     diablo
    1.49
    Activations Density 0.047%

    No Known Activations