© 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. 104503
    Prev
    Next
    INDEX
    Explanations

    multi-lingual common function words

    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
     oftentimes
    -1.68
     classy
    -1.55
     sehr
    -1.51
     supremely
    -1.47
     amidst
    -1.40
     sizeable
    -1.39
     for
    -1.38
     unrelenting
    -1.38
     perpetually
    -1.37
     if
    -1.34
    POSITIVE LOGITS
     XNUMX
    1.58
    かっこ
    1.55
     certamente
    1.54
     amd
    1.50
     և
    1.43
    @#
    1.41
     crucial
    1.41
     ​​
    1.40
    glad
    1.38
     ™
    1.36
    Activations Density 0.034%

    No Known Activations