© 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. 22-GEMMASCOPE-RES-131K
    7. 66692
    Prev
    Next
    INDEX
    Explanations

    levels, depositing, reap

    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_22/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
     both
    -1.45
     either
    -0.93
     beider
    -0.92
    name
    -0.91
     to
    -0.91
     before
    -0.90
    Both
    -0.88
    wise
    -0.86
     while
    -0.82
     concentrates
    -0.82
    POSITIVE LOGITS
     cinquième
    1.13
     tournoi
    1.04
     zimowe
    1.00
     Meksiko
    0.99
     inmediatamente
    0.98
    TagHelpers
    0.95
     verdaderamente
    0.95
     ilgi
    0.95
     بدون
    0.95
    ÄR
    0.94
    Activations Density 0.058%

    No Known Activations