© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57534
    Prev
    Next
    INDEX
    Explanations

    grammatical 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_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
     of
    -1.61
     this
    -1.45
     and
    -1.42
    p
    -1.37
     pouze
    -1.34
     either
    -1.26
     elet
    -1.26
    nt
    -1.23
     prese
    -1.23
     ></
    -1.20
    POSITIVE LOGITS
     nové
    1.59
     récente
    1.38
     florales
    1.38
     sposob
    1.38
     új
    1.37
     moje
    1.34
     farbe
    1.34
     surpren
    1.33
    řízení
    1.33
    дела
    1.33
    Activations Density 0.044%

    No Known Activations