© 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. 54104
    Prev
    Next
    INDEX
    Explanations

    dividing into groups or series

    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
     different
    -1.82
     various
    -1.38
     another
    -1.23
     each
    -1.21
     or
    -1.19
     differ
    -1.14
     різних
    -1.13
     differs
    -1.13
     other
    -1.12
     differed
    -1.12
    POSITIVE LOGITS
     where
    1.16
     which
    1.05
    😮
    1.04
     tica
    1.04
    😞
    1.02
    inches
    1.02
     wherein
    0.99
     وهو
    0.99
    😪
    0.97
     for
    0.95
    Activations Density 0.095%

    No Known Activations