© 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. 119880
    Prev
    Next
    INDEX
    Explanations

    links and code sources

    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
    each
    -0.06
     ensures
    -0.06
     newcomers
    -0.06
     geçen
    -0.06
     garantizar
    -0.06
     হাস্য
    -0.06
     administration
    -0.05
     issues
    -0.05
     conducts
    -0.05
     ensure
    -0.05
    POSITIVE LOGITS
     분명
    0.07
    IMI
    0.06
    řej
    0.06
     मुख्यमंत्री
    0.06
    haft
    0.06
    萜
    0.06
    一直是
    0.06
     webhook
    0.06
    ――――
    0.06
    までは
    0.06
    Activations Density 0.005%

    No Known Activations