© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10958
    Prev
    Next
    INDEX
    Explanations

    preceded by « or »

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

    std::cout and std::endl usage

    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_40_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
    Tagged
    0.42
    뤽
    0.41
     नज़र
    0.39
    Eye
    0.39
    )^{*
    0.39
     Eye
    0.38
    )^*
    0.38
    지가
    0.38
     Дей
    0.38
    (`${
    0.37
    POSITIVE LOGITS
     endl
    0.82
    endl
    0.79
     <<
    0.66
     setw
    0.65
    <<
    0.59
    flush
    0.57
     flush
    0.55
    <<"
    0.54
    iend
    0.54
     Flush
    0.54
    Activations Density 0.022%

    No Known Activations