© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130072
    Prev
    Next
    INDEX
    Explanations

    academic degrees and majors

    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
     melalui
    -0.10
    同樣
    -0.07
     nuestras
    -0.07
     bulunan
    -0.07
     Через
    -0.06
     nossas
    -0.06
    дям
    -0.06
     distinctive
    -0.06
     naše
    -0.06
     attraverso
    -0.06
    POSITIVE LOGITS
     изу
    0.06
     상관
    0.06
    _
    0.06
     документов
    0.06
     Exchanges
    0.05
     ער
    0.05
     लिविंग
    0.05
    atea
    0.05
    leges
    0.05
    afka
    0.05
    Activations Density 0.009%

    No Known Activations