© 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. 128620
    Prev
    Next
    INDEX
    Explanations

    ask your

    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
     بسیار
    -0.06
     entscheiden
    -0.06
     Decide
    -0.06
     ১ম
    -0.06
     décider
    -0.06
    while
    -0.06
     વિચાર
    -0.06
    Determine
    -0.06
     yourself
    -0.06
    非常的
    -0.06
    POSITIVE LOGITS
    他们的
    0.08
     jejich
    0.07
     их
    0.07
    他們
    0.07
    他们
    0.06
     عندهم
    0.06
    他們的
    0.06
     Specifically
    0.06
          
    0.06
     mereka
    0.06
    Activations Density 0.008%

    No Known Activations