© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26778
    Prev
    Next
    INDEX
    Explanations

    code and programming languages

    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
     ребенка
    -0.98
     akong
    -0.88
    paused
    -0.81
    ဵ
    -0.79
    puis
    -0.79
     aftermath
    -0.79
    kaw
    -0.78
    ppu
    -0.78
     erklä
    -0.78
     चाहिए
    -0.78
    POSITIVE LOGITS
     if
    1.48
     again
    0.97
    좁
    0.95
     until
    0.93
    Größe
    0.93
    Kein
    0.91
     Vem
    0.91
     before
    0.91
     while
    0.88
     had
    0.87
    Activations Density 0.001%

    No Known Activations