© 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. 116572
    Prev
    Next
    INDEX
    Explanations

    locations, diagnosis, year

    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
    -0.07
    oxygène
    -0.06
     அதன்
    -0.06
     শ্রেণী
    -0.06
    Indexer
    -0.05
    ^{+}$.
    -0.05
    🧡
    -0.05
     एकड़
    -0.05
     ஆகியோர்
    -0.05
     requisite
    -0.05
    POSITIVE LOGITS
     ∼
    0.08
     सालाना
    0.07
     what
    0.07
    when
    0.06
     now
    0.06
    每年
    0.06
    ∼
    0.06
    Now
    0.06
     every
    0.06
     Halloween
    0.06
    Activations Density 0.001%

    No Known Activations