© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130485
    Prev
    Next
    INDEX
    Explanations

    jsfiddle or plnkr links

    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
     estábamos
    -0.06
     др
    -0.06
     সঙ্গ
    -0.06
     குறிப்பிட்ட
    -0.05
    ↵
    -0.05
    لې
    -0.05
     was
    -0.05
     lên
    -0.05
    ិត្ត
    -0.05
     süt
    -0.05
    POSITIVE LOGITS
     THAT
    0.07
     accred
    0.07
    That
    0.06
     неправи
    0.06
     That
    0.06
     अनियमित
    0.06
    irregular
    0.06
     franchisee
    0.06
     alebo
    0.06
     더
    0.06
    Activations Density 0.015%

    No Known Activations