© 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. 10-GEMMASCOPE-RES-131K
    7. 85143
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners or nouns

    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
     coś
    -1.33
     use
    -1.30
     wykorzyst
    -1.17
     types
    -1.17
    rindo
    -1.14
    }
    -1.14
     använda
    -1.13
    </h4>
    -1.11
    bujete
    -1.11
     utilizan
    -1.10
    POSITIVE LOGITS
    кость
    1.36
    яз
    1.23
    undan
    1.19
    Etimología
    1.17
     أيضا
    1.16
    AccessorTable
    1.14
     soigneusement
    1.13
     също
    1.11
     &
    1.10
     おしゃれ
    1.10
    Activations Density 0.170%

    No Known Activations