© 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. 120384
    Prev
    Next
    INDEX
    Explanations

    year, Apple, Q, V, Expression

    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
     তাহারই
    -0.07
    还会
    -0.07
     indirect
    -0.07
     স্ত্র
    -0.06
    肯定
    -0.06
     ನಡುವ
    -0.06
    一定会
    -0.06
     باید
    -0.06
     annum
    -0.06
    Jean
    -0.06
    POSITIVE LOGITS
     suddenly
    0.06
     tenfold
    0.06
     changed
    0.06
     imaginable
    0.06
     deadly
    0.06
     questions
    0.06
     plötzlich
    0.06
     pedagog
    0.06
     tightened
    0.06
     exponentially
    0.06
    Activations Density 0.002%

    No Known Activations