© 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. 116820
    Prev
    Next
    INDEX
    Explanations

    Transanal

    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
     včetně
    -0.07
     není
    -0.07
     mnoho
    -0.07
     всеми
    -0.07
     모든
    -0.06
     सभी
    -0.06
     všech
    -0.06
     bếp
    -0.06
     mourn
    -0.06
     بسیاری
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.06
    कृत
    0.06
     मौजूद
    0.06
     prv
    0.05
     invece
    0.05
     Instead
    0.05
     revital
    0.05
     இவற்ற
    0.05
    க்கே
    0.05
     regularmente
    0.05
    Activations Density 0.001%

    No Known Activations