© 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. 118095
    Prev
    Next
    INDEX
    Explanations

    journal references and numbers

    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
     दिक्कत
    -0.07
     Altogether
    -0.06
     আলাদা
    -0.06
     ambienti
    -0.06
     secretory
    -0.06
     সমষ্টি
    -0.06
     evid
    -0.06
     metaphys
    -0.06
     연구
    -0.06
     иссле
    -0.06
    POSITIVE LOGITS
     extremely
    0.07
    往往
    0.07
     Extremely
    0.07
    extremely
    0.06
    所謂
    0.06
     혹은
    0.06
    dari
    0.06
     extraordinarily
    0.06
     weekly
    0.06
     reforma
    0.06
    Activations Density 0.003%

    No Known Activations