© 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. 27753
    Prev
    Next
    INDEX
    Explanations

    items and accessories

    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
     различни
    -1.63
     разных
    -1.51
     różne
    -1.49
     разные
    -1.41
     різних
    -1.25
     oamenii
    -1.19
     mépris
    -1.19
     różnych
    -1.18
     oameni
    -1.18
     основном
    -1.17
    POSITIVE LOGITS
     you
    2.16
     makes
    1.58
     make
    1.58
     your
    1.42
     so
    1.39
     truly
    1.35
     gives
    1.29
     just
    1.27
     give
    1.26
     all
    1.24
    Activations Density 0.025%

    No Known Activations