© 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. 128984
    Prev
    Next
    INDEX
    Explanations

    new, novel, unique, strange

    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
     karena
    -0.07
     those
    -0.07
     потому
    -0.06
     کشورهای
    -0.06
    oweit
    -0.06
    最初に
    -0.06
     fh
    -0.06
    Karena
    -0.06
     Gauteng
    -0.06
    보면
    -0.06
    POSITIVE LOGITS
     new
    0.08
     başka
    0.07
     another
    0.07
     strange
    0.07
     অদ্ভুত
    0.07
     नई
    0.06
     unexpected
    0.06
    如同
    0.06
     другой
    0.06
     innego
    0.06
    Activations Density 0.065%

    No Known Activations