© 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. 118565
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns followed by nouns

    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
     producen
    -0.07
    😊
    -0.07
     posso
    -0.07
     foto
    -0.07
     favorites
    -0.07
     favourites
    -0.07
     drawbacks
    -0.06
     😁
    -0.06
     പോലെ
    -0.06
     etik
    -0.06
    POSITIVE LOGITS
     all
    0.07
     ധാ
    0.06
    そういう
    0.06
    所有的
    0.06
     एक
    0.06
     toutes
    0.06
     മനസ്സ
    0.06
     tất
    0.06
     re
    0.06
     அனைத்து
    0.06
    Activations Density 0.004%

    No Known Activations