© 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. 7042
    Prev
    Next
    INDEX
    Explanations

    preposition followed by "the" or "this"

    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
     kullanılan
    -1.02
     roughly
    -1.00
     many
    -0.99
     reinen
    -0.99
     duży
    -0.97
     something
    -0.97
     duże
    -0.97
     aproximativ
    -0.97
     a
    -0.96
     everything
    -0.96
    POSITIVE LOGITS
     the
    1.62
     us
    1.55
     türk
    1.08
     klinik
    1.03
    เรา
    1.03
     and
    1.02
     katalog
    1.02
     me
    1.02
    🚶
    1.01
    我們
    0.99
    Activations Density 0.045%

    No Known Activations