© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9917
    Prev
    Next
    INDEX
    Explanations

    code assignment with equals

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

    converting or modifying values

    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
     મારા
    0.42
    জাত
    0.41
    他說
    0.41
    他说
    0.41
    不上
    0.39
    <0xEA>
    0.39
    ńca
    0.39
    bigsqcup
    0.39
    舀
    0.39
    ည့်
    0.38
    POSITIVE LOGITS
     >>=
    0.74
     %=
    0.71
     *=
    0.64
     -=
    0.61
    -=
    0.52
     converted
    0.52
     &=
    0.50
     /=
    0.50
     $=$
    0.48
    %=
    0.47
    Activations Density 0.001%

    No Known Activations