© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116435
    Prev
    Next
    INDEX
    Explanations

    conditional statements and loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.07
                     
    -0.06
    ↵
    -0.06
    AH
    -0.05
                           
    -0.05
           
    -0.05
     Lorem
    -0.05
    The
    -0.05
    ↵↵
    -0.05
    =
    -0.05
    POSITIVE LOGITS
     என்பது
    0.08
     শুধু
    0.07
     多く
    0.07
     говорят
    0.07
     通常
    0.07
    說是
    0.07
     મુખ્ય
    0.07
     Plusieurs
    0.07
    大约
    0.07
     amely
    0.07
    Activations Density 0.003%

    No Known Activations