© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130789
    Prev
    Next
    INDEX
    Explanations

    possessive marker followed by noun

    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
     svih
    -0.07
    끅
    -0.07
    那么多
    -0.06
     reputation
    -0.06
     والتي
    -0.06
    ર્થ
    -0.06
     всех
    -0.06
     vielfält
    -0.06
     является
    -0.06
     burials
    -0.06
    POSITIVE LOGITS
    ,
    0.07
    、
    0.06
     همین
    0.06
     비슷한
    0.06
     similar
    0.06
     مشابه
    0.06
     conta
    0.06
     ஞ
    0.05
    similar
    0.05
    Accom
    0.05
    Activations Density 0.006%

    No Known Activations