© 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. 118365
    Prev
    Next
    INDEX
    Explanations

    court of appeals or criminal appeals

    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
     ಔ
    -0.06
     கடை
    -0.06
     and
    -0.06
     gelegen
    -0.05
     combines
    -0.05
     सम्मिलित
    -0.05
    **
    -0.05
     rimu
    -0.05
    非常に
    -0.05
     অপার
    -0.05
    POSITIVE LOGITS
     gilded
    0.06
     ผู้
    0.06
     biotech
    0.06
    砷
    0.06
     Schritte
    0.06
     persön
    0.06
     ludzie
    0.06
    开始了
    0.06
     journalist
    0.06
    シップ
    0.05
    Activations Density 0.006%

    No Known Activations