© 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. 129193
    Prev
    Next
    INDEX
    Explanations

    synthesis of chemical compounds

    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
     inac
    -0.07
     dello
    -0.06
     Molecules
    -0.06
     наших
    -0.06
     svih
    -0.05
    lobby
    -0.05
     Initially
    -0.05
    מל
    -0.05
     Although
    -0.05
     развед
    -0.05
    POSITIVE LOGITS
    她说
    0.07
     setzen
    0.06
     other
    0.06
     neighbourhood
    0.06
     Это
    0.06
    进一步
    0.06
    说什么
    0.06
     Geschichte
    0.06
    下一步
    0.06
     weiter
    0.06
    Activations Density 0.014%

    No Known Activations