© 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. 34-GEMMASCOPE-RES-131K
    7. 75614
    Prev
    Next
    INDEX
    Explanations

    prepositions and similar words

    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
     pasirink
    -1.14
     vienas
    -1.07
     pagrind
    -1.02
     kiek
    -1.00
     vaiz
    -0.99
     noong
    -0.99
     iyon
    -0.97
     atlik
    -0.94
     duomen
    -0.94
     iyong
    -0.94
    POSITIVE LOGITS
     at
    4.44
     при
    4.44
     při
    4.03
     bei
    3.59
     عند
    3.42
     przy
    3.34
     beim
    2.95
     dabei
    2.73
     upon
    2.59
     bij
    2.33
    Activations Density 0.019%

    No Known Activations