© 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. 10-GEMMASCOPE-RES-131K
    7. 12360
    Prev
    Next
    INDEX
    Explanations

    plural nouns and categories

    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_10/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
     when
    -1.63
     after
    -1.63
     six
    -1.52
     because
    -1.50
     When
    -1.49
     ketika
    -1.44
     at
    -1.41
    ִּ
    -1.35
     so
    -1.35
     whose
    -1.34
    POSITIVE LOGITS
    鹩
    1.56
     beschränkt
    1.32
     nogle
    1.32
    hopefully
    1.27
     permettre
    1.27
     to
    1.23
     inapropiados
    1.23
    睃
    1.22
     nuovi
    1.22
     decisões
    1.21
    Activations Density 1.773%

    No Known Activations