© 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. 128464
    Prev
    Next
    INDEX
    Explanations

    month day

    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
     phrasing
    -0.07
     creating
    -0.07
     one
    -0.07
    通过
    -0.06
     establishing
    -0.06
    หลังจาก
    -0.06
     yaparak
    -0.06
     ৭৫
    -0.06
     नेहमी
    -0.06
     автором
    -0.06
    POSITIVE LOGITS
     ওখানে
    0.06
    <0xB5>
    0.06
     rencontrer
    0.06
     Bangladeshi
    0.06
    child
    0.06
     vilka
    0.06
     présentes
    0.06
     దాని
    0.06
     stvari
    0.06
     فى
    0.06
    Activations Density 0.017%

    No Known Activations