© 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. 22-GEMMASCOPE-RES-131K
    7. 98223
    Prev
    Next
    INDEX
    Explanations

    HTML table cells

    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_22/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
     really
    -1.30
     truly
    -1.22
     absolutely
    -1.11
     totally
    -1.11
     и
    -1.10
     continual
    -1.09
     by
    -1.07
     getting
    -1.05
     fairly
    -1.03
     very
    -1.01
    POSITIVE LOGITS
    
    1.33
     vermelho
    1.13
     diário
    1.07
     إد
    1.06
    跟你
    1.05
    睃
    1.05
     INDEPENDENT
    1.02
    夀
    1.02
     männer
    1.02
     intención
    1.02
    Activations Density 0.005%

    No Known Activations