© 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. 34-GEMMASCOPE-RES-131K
    7. 615
    Prev
    Next
    INDEX
    Explanations

    plural nouns in lists

    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_34/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
     in
    -1.53
     at
    -1.45
     on
    -1.29
     one
    -1.23
     each
    -1.22
     only
    -1.20
     before
    -1.17
     through
    -1.16
     all
    -1.15
     after
    -1.14
    POSITIVE LOGITS
     and
    1.96
     februari
    1.44
    messi
    1.42
     véhic
    1.38
     allerlei
    1.32
     rafraî
    1.32
    iamo
    1.31
    llllll
    1.29
     januari
    1.29
     perpé
    1.28
    Activations Density 0.163%

    No Known Activations