© 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. 39347
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
     but
    -1.77
     just
    -1.66
     then
    -1.61
     now
    -1.41
     even
    -1.36
     that
    -1.14
     But
    -1.14
     लेकिन
    -1.13
     dennoch
    -1.13
     trotzdem
    -1.09
    POSITIVE LOGITS
     sebelumnya
    1.19
     wcześniej
    1.16
     focuses
    1.11
     discul
    1.09
    aim
    1.09
    ЗЫ
    1.08
    specifically
    1.07
     we
    1.05
     Specifically
    1.02
     reú
    1.02
    Activations Density 0.337%

    No Known Activations