© 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. 120209
    Prev
    Next
    INDEX
    Explanations

    Ottoman words

    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
     Cette
    -0.07
     ಯಾವ
    -0.06
     Když
    -0.06
     vollständig
    -0.06
     Where
    -0.06
    是将
    -0.06
     ninguno
    -0.06
     reli
    -0.06
     nazionali
    -0.06
     சொந்த
    -0.06
    POSITIVE LOGITS
     "
    0.06
    SUFFIX
    0.05
    訢
    0.05
    <0xE2>
    0.05
    اده
    0.05
    緍
    0.05
    words
    0.05
    username
    0.05
    "
    0.05
     turnaround
    0.05
    Activations Density 0.002%

    No Known Activations