© 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. 10-GEMMASCOPE-RES-131K
    7. 59362
    Prev
    Next
    INDEX
    Explanations

    citations and abbreviations

    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
    If
    -2.03
     two
    -2.03
     requirements
    -1.94
     then
    -1.87
     even
    -1.76
     new
    -1.76
     biggest
    -1.75
    :
    -1.73
     including
    -1.73
    _
    -1.70
    POSITIVE LOGITS
    
    1.77
    TODOS
    1.68
     rése
    1.50
    撵
    1.49
    Batis
    1.49
     semblent
    1.48
    篾
    1.48
     trám
    1.47
    ⢧
    1.45
    Carex
    1.44
    Activations Density 0.003%

    No Known Activations