© 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. 11244
    Prev
    Next
    INDEX
    Explanations

    compound modifiers

    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
     AMAZING
    -1.41
     wondrous
    -1.32
     และ
    -1.30
     diverses
    -1.29
     VERY
    -1.27
     REALLY
    -1.26
     ornate
    -1.26
     современной
    -1.24
     momentous
    -1.24
     EVEN
    -1.23
    POSITIVE LOGITS
     when
    1.80
     as
    1.80
     because
    1.77
     after
    1.77
     it
    1.66
     with
    1.64
     just
    1.53
     one
    1.50
     Since
    1.45
     should
    1.42
    Activations Density 0.131%

    No Known Activations