© 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. 129110
    Prev
    Next
    INDEX
    Explanations

    numbers, decimals, and specific names

    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
     on
    -0.07
     одну
    -0.06
    依照
    -0.06
     each
    -0.06
    fail
    -0.06
     obrigado
    -0.05
    Smooth
    -0.05
    各
    -0.05
     ক্ষুধার
    -0.05
    uria
    -0.05
    POSITIVE LOGITS
     buvo
    0.07
     substantially
    0.07
     же
    0.07
     kunna
    0.06
    ዲስ
    0.06
     crucially
    0.06
     vitally
    0.06
     CEO
    0.06
     hochwert
    0.06
    普通の
    0.06
    Activations Density 0.004%

    No Known Activations