© 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. 119631
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
     bruk
    -0.07
     people
    -0.06
    each
    -0.06
    建议
    -0.06
     আপনা
    -0.06
     લોકો
    -0.06
     chaque
    -0.06
    当你
    -0.06
     its
    -0.06
    ഞ്ച്
    -0.06
    POSITIVE LOGITS
     আলোচিত
    0.07
     그는
    0.07
    这位
    0.07
     positions
    0.06
     nagyon
    0.06
    這位
    0.06
     매우
    0.06
     flawless
    0.06
     väga
    0.06
     Здравствуйте
    0.06
    Activations Density 0.009%

    No Known Activations