© 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. 119820
    Prev
    Next
    INDEX
    Explanations

    suggesting conclusions or implications

    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
     confirms
    -0.07
     constituted
    -0.06
     fails
    -0.06
     examines
    -0.06
     знаний
    -0.06
    })=\
    -0.06
     तत्काल
    -0.06
    稱
    -0.06
     threatens
    -0.06
     constitutes
    -0.06
    POSITIVE LOGITS
     mungkin
    0.06
     Russie
    0.06
     deliberately
    0.06
    खाली
    0.06
     ব্রি
    0.06
     iza
    0.06
     chyba
    0.06
     purposely
    0.06
    сел
    0.06
     медицин
    0.06
    Activations Density 0.007%

    No Known Activations