© 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. 119806
    Prev
    Next
    INDEX
    Explanations

    version 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
     started
    -0.07
    Proposal
    -0.06
     quoi
    -0.06
    Another
    -0.06
     faster
    -0.06
    emers
    -0.06
     empezó
    -0.06
     postup
    -0.06
     tidak
    -0.06
    కాలు
    -0.06
    POSITIVE LOGITS
    關鍵
    0.07
    ในการ
    0.06
    同年
    0.06
     परिस्थिति
    0.06
     بينما
    0.06
     generalmente
    0.06
    deki
    0.06
    에서도
    0.06
     sehr
    0.06
    にも
    0.06
    Activations Density 0.004%

    No Known Activations