© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118481
    Prev
    Next
    INDEX
    Explanations

    completes, finishing, complement

    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
     bikinis
    -1.02
     iniziato
    -0.94
    ụp
    -0.91
    tủ
    -0.91
     saree
    -0.90
    grafías
    -0.90
     zelfs
    -0.89
     reimbur
    -0.88
     after
    -0.88
    ૮
    -0.87
    POSITIVE LOGITS
     completes
    1.59
     finishing
    1.59
     complement
    1.55
     Completing
    1.31
     completing
    1.31
     finish
    1.30
     accessor
    1.30
     finished
    1.30
     completed
    1.28
     accessories
    1.28
    Activations Density 0.011%

    No Known Activations