© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14361
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions connecting words

    np_acts-logits-general · gemini-2.5-flash-lite

    auto ; clauses :**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wad
    0.45
     aand
    0.45
     paving
    0.45
     ditt
    0.44
     nurturing
    0.44
    inand
    0.43
    keeping
    0.42
     व
    0.42
    nhold
    0.41
     boring
    0.41
    POSITIVE LOGITS
    г
    0.53
    з
    0.52
    ле
    0.51
    тр
    0.51
    Produtos
    0.50
    ر
    0.48
    র্ডার
    0.48
    ື້ນ
    0.47
    ме
    0.47
    зира
    0.47
    Activations Density 0.001%

    No Known Activations