© 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. 119009
    Prev
    Next
    INDEX
    Explanations

    specific date or name follows

    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
    經營
    -0.07
     برخی
    -0.07
    Algun
    -0.07
     algunos
    -0.07
     일부
    -0.06
    始め
    -0.06
    这一点
    -0.06
     ça
    -0.06
     niektó
    -0.06
     некоторы
    -0.06
    POSITIVE LOGITS
     jeweiligen
    0.07
     policial
    0.06
     সমাবেশে
    0.06
     historii
    0.06
     filmes
    0.06
    empat
    0.06
    getattr
    0.06
    感覚
    0.06
    ٠
    0.06
     surprising
    0.06
    Activations Density 0.010%

    No Known Activations