© 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. 64714
    Prev
    Next
    INDEX
    Explanations

    legal document citations and headers

    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
     krijgen
    -0.94
    anglès
    -0.90
     Cama
    -0.77
     résister
    -0.73
    ontin
    -0.73
    ndia
    -0.71
    liberal
    -0.70
    娆
    -0.70
    时期
    -0.70
     체
    -0.70
    POSITIVE LOGITS
     trailing
    0.81
     aprove
    0.75
     leading
    0.75
    
    0.75
     Leading
    0.72
     deductible
    0.70
    Leading
    0.70
     faults
    0.66
    trailing
    0.66
     leads
    0.65
    Activations Density 0.045%

    No Known Activations