© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    class action and intervention plaintiffs

    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
    ↵↵
    -2.06
     In
    -1.94
    In
    -1.85
            
    -1.79
                
    -1.66
    The
    -1.59
     .
    -1.56
     changes
    -1.55
     (
    -1.55
          
    -1.54
    POSITIVE LOGITS
    ⵌ
    1.74
    ípio
    1.65
     Reſ
    1.61
    PlayerPrefs
    1.59
    ">\
    1.57
     歴史
    1.56
    Probl
    1.55
     なく
    1.49
     vaikka
    1.48
     kupa
    1.48
    Activations Density 0.013%

    No Known Activations