© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    sports competitions and races

    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
     who
    -1.80
     current
    -1.20
     originally
    -1.19
     about
    -1.16
     currently
    -1.16
    仕事を
    -1.16
     insumos
    -1.15
     nobody
    -1.13
     that
    -1.11
     things
    -1.09
    POSITIVE LOGITS
    ຣ
    1.26
     months
    1.22
     بيها
    1.21
     internationale
    1.14
     ihrem
    1.14
    цер
    1.13
     هذا
    1.07
     міся
    1.05
     европей
    1.05
    month
    1.04
    Activations Density 0.048%

    No Known Activations