© 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. 130668
    Prev
    Next
    INDEX
    Explanations

    from or by

    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
    のです
    -0.08
    アプリケーション
    -0.07
     temor
    -0.07
     tehát
    -0.07
     realiza
    -0.06
    を実現
    -0.06
     केंद्रित
    -0.06
     เรียก
    -0.06
    콧
    -0.06
     можем
    -0.06
    POSITIVE LOGITS
    reviewed
    0.06
     loads
    0.06
    sized
    0.06
    from
    0.06
     Denise
    0.06
     comfort
    0.06
     promo
    0.06
     burglary
    0.06
     fotos
    0.06
    attached
    0.05
    Activations Density 0.033%

    No Known Activations