© 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. 22-GEMMASCOPE-RES-131K
    7. 26898
    Prev
    Next
    INDEX
    Explanations

    company, group, or subsidiary

    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
     new
    -1.22
     especially
    -1.12
    女的
    -1.09
     topics
    -1.09
     test
    -1.07
     require
    -1.05
     nuevamente
    -1.05
     Erziehung
    -1.04
     time
    -1.03
     collaboration
    -1.03
    POSITIVE LOGITS
     siè
    1.38
     hilos
    1.13
     parall
    1.13
     ibang
    1.05
     éte
    1.05
     corriger
    1.05
     kopen
    1.05
     précédentes
    1.04
     BOU
    1.03
     other
    1.02
    Activations Density 0.062%

    No Known Activations