© 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. 9777
    Prev
    Next
    INDEX
    Explanations

    such or said followed by a noun

    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
     spolup
    -1.34
     podremos
    -1.32
     tendremos
    -1.28
     zlep
    -1.28
    exercice
    -1.23
     levar
    -1.23
    epy
    -1.23
     decimos
    -1.22
     zů
    -1.21
     znamená
    -1.20
    POSITIVE LOGITS
     层
    1.23
     extensive
    1.17
     additional
    1.13
     without
    1.13
     erit
    1.12
     最后
    1.12
     continuing
    1.10
     necessaria
    1.10
     immaculate
    1.09
    二十四
    1.09
    Activations Density 0.023%

    No Known Activations