© 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. 119514
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

    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
     još
    -0.07
    jag
    -0.07
     ещё
    -0.07
     સમયે
    -0.06
     jeszcze
    -0.06
     еще
    -0.06
    여기
    -0.06
    𝑏
    -0.06
    這裡
    -0.06
    まだ
    -0.06
    POSITIVE LOGITS
     versus
    0.07
     dedicata
    0.06
     endeavors
    0.06
    다고
    0.06
    As
    0.06
     prestige
    0.06
     cornerstone
    0.05
     fervor
    0.05
     famed
    0.05
    পক্ষে
    0.05
    Activations Density 0.003%

    No Known Activations