© 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. 34-GEMMASCOPE-RES-131K
    7. 77322
    Prev
    Next
    INDEX
    Explanations

    subject followed by verb or action

    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_34/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
     gotten
    -0.97
    × 
    -0.91
     różne
    -0.90
    真的是
    -0.90
    жении
    -0.89
    んでる
    -0.89
     száz
    -0.87
    )—
    -0.86
     goin
    -0.86
     zwykle
    -0.86
    POSITIVE LOGITS
     duly
    1.27
     dianteiro
    0.97
     quiz
    0.96
     curry
    0.95
     swagger
    0.94
     tot
    0.92
    Đối
    0.89
     christ
    0.87
    Fonto
    0.85
     ply
    0.84
    Activations Density 0.097%

    No Known Activations