© 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. 15434
    Prev
    Next
    INDEX
    Explanations

    program

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

    program or programmed AI assistant

    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
    <0x91>
    0.71
    to
    0.70
    le
    0.67
    EN
    0.64
    of
    0.63
    のは
    0.63
    bahan
    0.62
    iche
    0.61
    ).
    0.60
    p
    0.60
    POSITIVE LOGITS
     programu
    1.33
     programma
    1.30
     programmi
    1.26
     programas
    1.22
     البرنامج
    1.17
     programmes
    1.14
     Programa
    1.13
     프로그램
    1.12
     программы
    1.10
     programs
    1.09
    Activations Density 0.352%

    No Known Activations