© 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. 34-GEMMASCOPE-RES-131K
    7. 106512
    Prev
    Next
    INDEX
    Explanations

    only specific items

    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
    走吧
    -0.99
     normaal
    -0.92
     verschiedene
    -0.92
     verschiedenen
    -0.91
     eksempel
    -0.91
    ままで
    -0.88
     bedrijfs
    -0.87
     utilizada
    -0.85
     différentes
    -0.84
    
    -0.84
    POSITIVE LOGITS
     those
    2.13
     olyan
    1.98
     những
    1.91
     aquellas
    1.90
     products
    1.90
     projects
    1.83
     companies
    1.79
     items
    1.73
     ones
    1.71
     sites
    1.71
    Activations Density 0.510%

    No Known Activations