© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120994
    Prev
    Next
    INDEX
    Explanations

    stock offering, cargo carriers, password hacks

    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
    Negative Logits
     toilet
    -0.07
    這些
    -0.07
     harder
    -0.07
    这些
    -0.07
     tých
    -0.07
     those
    -0.07
     socalled
    -0.06
     সাহসী
    -0.06
     этих
    -0.06
    我們可以
    -0.06
    POSITIVE LOGITS
    <0xE3>
    0.07
     (-
    0.06
     terminated
    0.06
     நிறுவனம்
    0.06
    ғ
    0.05
     olmadığı
    0.05
    axes
    0.05
     permasalahan
    0.05
     axes
    0.05
     comunque
    0.05
    Activations Density 0.003%

    No Known Activations