© 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. 118089
    Prev
    Next
    INDEX
    Explanations

    asking for suggestions or ideas?

    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
    男
    -0.06
    ;
    -0.06
     contrasted
    -0.05
     što
    -0.05
    真实的
    -0.05
    和
    -0.05
     mountaine
    -0.05
     какая
    -0.05
     люблю
    -0.05
     juicy
    -0.05
    POSITIVE LOGITS
     search
    0.07
    搜索
    0.07
     বিশেষভাবে
    0.07
    에서는
    0.07
    ながら
    0.07
    mittag
    0.06
     অনেকটাই
    0.06
     अस्वी
    0.06
     includes
    0.06
     উভয়
    0.06
    Activations Density 0.014%

    No Known Activations