© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66479
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     who
    -1.99
     ་
    -1.77
    
    -1.65
     donne
    -1.58
    ⸻
    -1.51
     vícti
    -1.50
     crimen
    -1.50
    がなく
    -1.50
     casse
    -1.47
     incidente
    -1.46
    POSITIVE LOGITS
     and
    2.38
     an
    1.80
     мы
    1.69
     with
    1.67
     two
    1.62
    我們
    1.56
     Daarna
    1.54
     Drittel
    1.53
     Terbaru
    1.52
     one
    1.51
    Activations Density 0.093%

    No Known Activations