© 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. 130568
    Prev
    Next
    INDEX
    Explanations

    two cubs

    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
     cualquier
    -0.08
     милли
    -0.07
     প্রেসিডেন্ট
    -0.06
     Cualquier
    -0.06
     های
    -0.06
     живота
    -0.06
    Ahmed
    -0.06
     médico
    -0.06
    Then
    -0.06
     VIP
    -0.06
    POSITIVE LOGITS
     somente
    0.06
     soms
    0.06
     gpm
    0.06
    そうです
    0.05
    各国
    0.05
     ফর্ম
    0.05
    retval
    0.05
     formula
    0.05
     sometimes
    0.05
    Instance
    0.05
    Activations Density 0.038%

    No Known Activations