© 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. 84014
    Prev
    Next
    INDEX
    Explanations

    after preposition

    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
     caisse
    -0.76
     midst
    -0.71
     Schumer
    -0.69
    òria
    -0.69
     quête
    -0.68
     しゃ
    -0.68
    WriteTo
    -0.67
     díl
    -0.67
    两只
    -0.66
    @@@@@
    -0.66
    POSITIVE LOGITS
     nacional
    0.67
    ovanie
    0.65
     обнов
    0.64
    瀑布
    0.63
    ガール
    0.63
     Kevin
    0.63
    berger
    0.62
    疾
    0.62
     Пол
    0.62
     Revolution
    0.62
    Activations Density 0.059%

    No Known Activations