© 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. 20243
    Prev
    Next
    INDEX
    Explanations

    code blocks with loops

    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
     only
    -1.77
     &
    -1.74
     just
    -1.65
     without
    -1.59
     no
    -1.58
     so
    -1.52
    $
    -1.50
     all
    -1.50
     to
    -1.47
    POSITIVE LOGITS
    隨著
    1.79
    因為
    1.78
     Atención
    1.77
    ༵
    1.70
     olika
    1.69
    赑
    1.66
    淠
    1.66
     Songtext
    1.66
    ৄ
    1.65
     are
    1.63
    Activations Density 0.008%

    No Known Activations