© 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. 116652
    Prev
    Next
    INDEX
    Explanations

    Org Foundation, authors, Argentina

    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
     business
    -0.07
     constantly
    -0.06
    க்கு
    -0.06
     следующих
    -0.06
    extend
    -0.06
     бизнес
    -0.06
    спомина
    -0.06
     liệt
    -0.06
     ಪ್ರಕಾರ
    -0.06
    อาจ
    -0.06
    POSITIVE LOGITS
    域名
    0.07
     unquestionably
    0.06
     แน
    0.06
     undersea
    0.06
     undeniably
    0.06
    即将
    0.06
     povinn
    0.06
     রক্ষার
    0.06
     mores
    0.06
    国内
    0.05
    Activations Density 0.013%

    No Known Activations