© 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. 128994
    Prev
    Next
    INDEX
    Explanations

    , ; and integer/long declarations

    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
     प्रौ
    -0.06
     的
    -0.06
     unanticipated
    -0.06
     belated
    -0.06
     typeof
    -0.06
     feas
    -0.06
     د
    -0.06
     আগ্রহ
    -0.06
     エ
    -0.05
     খো
    -0.05
    POSITIVE LOGITS
     wenn
    0.07
     lành
    0.07
     two
    0.07
     nenhum
    0.06
     Cuando
    0.06
     which
    0.06
    Register
    0.06
     Quando
    0.06
     damit
    0.06
     ninguno
    0.06
    Activations Density 0.001%

    No Known Activations