© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30844
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs following conjunctions

    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
     gruppe
    -1.45
     is
    -1.44
     maniere
    -1.41
    congrats
    -1.41
    ifies
    -1.41
     berge
    -1.39
     majest
    -1.39
     lande
    -1.39
     parut
    -1.38
     tempel
    -1.36
    POSITIVE LOGITS
     be
    5.13
     have
    2.73
     provide
    2.55
     become
    2.55
     give
    2.25
     make
    2.17
     take
    2.16
     may
    1.98
     come
    1.97
     remain
    1.95
    Activations Density 0.157%

    No Known Activations