© 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. 117411
    Prev
    Next
    INDEX
    Explanations

    headings in documents

    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
     ঐতিহাসিক
    -0.07
    通过
    -0.07
     नाकाम
    -0.07
     melalui
    -0.06
     importantly
    -0.06
     rejected
    -0.06
     ಮೂಲಕ
    -0.06
    通過
    -0.06
     প্রতিবেশী
    -0.06
     by
    -0.06
    POSITIVE LOGITS
     binge
    0.06
    elle
    0.06
     Sugar
    0.05
    USB
    0.05
     progetto
    0.05
     Barry
    0.05
    are
    0.05
     jsou
    0.05
     ছাড়াও
    0.05
     tops
    0.05
    Activations Density 0.001%

    No Known Activations