© 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. 91308
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by proper 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_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
     whichever
    -0.90
    ของ
    -0.84
     ''
    -0.84
     ännu
    -0.84
    調味料
    -0.82
     expedite
    -0.82
    装修
    -0.81
     whoever
    -0.80
    Bson
    -0.80
    時期
    -0.78
    POSITIVE LOGITS
     leyendo
    1.06
    telor
    0.95
    nachweis
    0.95
     egne
    0.94
    >())
    0.93
     vrouw
    0.92
     SEÑ
    0.92
     liefde
    0.91
    өз
    0.90
    kään
    0.90
    Activations Density 0.025%

    No Known Activations