© 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. 130388
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     Dis
    -0.07
     любые
    -0.06
     pre
    -0.06
     உயிர
    -0.06
    dis
    -0.06
    Dis
    -0.06
    DIS
    -0.06
     любых
    -0.06
     emailed
    -0.06
     dis
    -0.06
    POSITIVE LOGITS
     too
    0.07
     تشکیل
    0.07
     hence
    0.07
     слишком
    0.06
     Hence
    0.06
    Too
    0.06
    Hence
    0.06
     ৷
    0.06
     assumption
    0.06
    ledovatel
    0.06
    Activations Density 0.004%

    No Known Activations