© 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. 292
    Prev
    Next
    INDEX
    Explanations

    nouns followed by prepositions

    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
     singur
    -1.19
    是这样
    -1.10
     scurt
    -1.07
    點擊
    -1.00
    圖片
    -1.00
    還會
    -1.00
     will
    -0.98
     astfel
    -0.98
     acesta
    -0.97
     acestea
    -0.97
    POSITIVE LOGITS
     of
    1.98
     that
    1.73
     to
    1.47
     kupa
    1.30
     maksi
    1.28
     maksimal
    1.27
     ekst
    1.25
     fabrik
    1.23
     elektri
    1.23
     for
    1.20
    Activations Density 0.053%

    No Known Activations