© 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. 116633
    Prev
    Next
    INDEX
    Explanations

    parsing JSON, script commands, string conversion

    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
     या
    -0.07
    または
    -0.07
     株式会社
    -0.07
     یا
    -0.07
     or
    -0.06
     cession
    -0.06
     আবির্ভাব
    -0.06
    unctional
    -0.06
    葡萄酒
    -0.06
    或者
    -0.06
    POSITIVE LOGITS
    fallback
    0.06
     internacional
    0.06
     Internationale
    0.06
     relied
    0.06
    毕业
    0.06
    อื่นๆ
    0.06
     (.
    0.06
     amplified
    0.06
    國際
    0.06
     artyku
    0.05
    Activations Density 0.048%

    No Known Activations