© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118602
    Prev
    Next
    INDEX
    Explanations

    improving something

    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
     и
    -0.08
     exquisite
    -0.07
     και
    -0.06
     ಕೆಲಸ
    -0.06
     amazing
    -0.06
     và
    -0.06
    桿
    -0.06
     판
    -0.06
    ..\
    -0.06
     artistic
    -0.06
    POSITIVE LOGITS
     logique
    0.06
     continually
    0.06
     intersections
    0.06
     intersects
    0.06
    ologue
    0.06
     মানুষকে
    0.06
     furthering
    0.06
     पीपल
    0.06
     discerning
    0.06
     only
    0.05
    Activations Density 0.033%

    No Known Activations