© 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. 116747
    Prev
    Next
    INDEX
    Explanations

    triglycerides and lipids

    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
    ختار
    -0.06
     निर्ण
    -0.06
    个数
    -0.06
     hillside
    -0.06
     their
    -0.06
    म्मत
    -0.05
     pieno
    -0.05
     scoreless
    -0.05
     physiologically
    -0.05
     wasteland
    -0.05
    POSITIVE LOGITS
    どん
    0.07
     വാഹന
    0.07
    occas
    0.06
     времен
    0.06
     flimsy
    0.06
    autions
    0.06
     critics
    0.06
     uzman
    0.06
     flanked
    0.06
     seasonal
    0.06
    Activations Density 0.003%

    No Known Activations