© 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. 120708
    Prev
    Next
    INDEX
    Explanations

    **US patent**

    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
     Smith
    -0.06
     خارجی
    -0.06
    Chinese
    -0.06
     także
    -0.06
     similar
    -0.06
     görd
    -0.06
     சரா
    -0.06
    ளாவ
    -0.06
    linux
    -0.06
     значи
    -0.05
    POSITIVE LOGITS
     vielleicht
    0.08
     perhaps
    0.07
     Perhaps
    0.07
    不可能
    0.07
    Perhaps
    0.07
    ielleicht
    0.07
     abbastanza
    0.06
     where
    0.06
     nicht
    0.06
     arguably
    0.06
    Activations Density 0.001%

    No Known Activations