© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    code comments and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bun
    1.57
     ASU
    1.55
     karst
    1.55
     สา
    1.54
     (#
    1.52
    VideoButton
    1.51
    Lun
    1.50
    
    1.50
     SRC
    1.48
     ресторан
    1.48
    POSITIVE LOGITS
    //
    0.82
     "//
    0.66
    //}
    0.62
    forEach
    0.61
     nullptr
    0.60
    ewood
    0.57
     diretta
    0.55
    //{
    0.55
    charAt
    0.54
     intervalles
    0.54
    Activations Density 0.118%

    No Known Activations