© 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. 128328
    Prev
    Next
    INDEX
    Explanations

    separators and titles

    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
     algunos
    -0.06
     niektor
    -0.06
     bustle
    -0.06
    hadoop
    -0.06
     некоторы
    -0.06
    ेटिव
    -0.06
    ğı
    -0.06
     بعض
    -0.06
     ряд
    -0.06
    എ
    -0.06
    POSITIVE LOGITS
    !,
    0.07
    !.
    0.07
     very
    0.06
    !",
    0.06
     even
    0.06
    继续
    0.06
     стала
    0.06
    !
    0.06
     incredibly
    0.06
     увидеть
    0.06
    Activations Density 0.001%

    No Known Activations