© 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. 108406
    Prev
    Next
    INDEX
    Explanations

    than anything

    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
     olika
    -1.11
     именно
    -1.02
    的主要
    -1.00
     verschiedenen
    -1.00
     vooral
    -0.94
     разных
    -0.93
    ofag
    -0.91
     verschiedene
    -0.90
     разные
    -0.90
     different
    -0.89
    POSITIVE LOGITS
     any
    2.80
    任何
    1.93
     qualquer
    1.84
     even
    1.83
     cualquier
    1.81
     anything
    1.79
     herhangi
    1.64
     любого
    1.59
     anyone
    1.57
     будь
    1.56
    Activations Density 0.038%

    No Known Activations