© 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. 129387
    Prev
    Next
    INDEX
    Explanations

    currency, finance, and places

    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
     flourished
    -0.07
    とても
    -0.06
     très
    -0.06
     очень
    -0.06
     জ্বাল
    -0.06
     bardzo
    -0.06
    ৫
    -0.06
     довольно
    -0.06
    攙
    -0.06
     muito
    -0.06
    POSITIVE LOGITS
     Other
    0.07
     U
    0.07
     OTHER
    0.06
     दर्
    0.06
     ಇತರ
    0.06
     other
    0.06
    ificant
    0.06
     Mike
    0.06
    dataGridView
    0.06
     You
    0.06
    Activations Density 0.002%

    No Known Activations