© 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. 128872
    Prev
    Next
    INDEX
    Explanations

    contraceptive, reversible, recording, copying

    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
     schnelle
    -0.07
    穩定
    -0.07
    效率
    -0.07
     Stability
    -0.07
     rédu
    -0.06
     eficiencia
    -0.06
    简化
    -0.06
     stability
    -0.06
     reduce
    -0.06
    稳定
    -0.06
    POSITIVE LOGITS
     আদম
    0.06
     refundable
    0.06
     международного
    0.06
    International
    0.06
     Los
    0.06
     adaption
    0.06
     चारों
    0.06
     International
    0.06
    £
    0.06
    Ĺ
    0.06
    Activations Density 0.045%

    No Known Activations