© 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. 10-GEMMASCOPE-RES-131K
    7. 113608
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
     sérieux
    -1.41
    approximately
    -1.40
     '?
    -1.35
     electricidad
    -1.34
    Inoltre
    -1.33
     bílá
    -1.31
     essas
    -1.29
     quindi
    -1.29
    Nokia
    -1.29
     Mereka
    -1.28
    POSITIVE LOGITS
     with
    2.06
     by
    1.88
     in
    1.80
     through
    1.59
     using
    1.54
     not
    1.48
     from
    1.43
     for
    1.42
     on
    1.39
     via
    1.35
    Activations Density 0.478%

    No Known Activations