© 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. 118291
    Prev
    Next
    INDEX
    Explanations

    Toxic anterior segment, ProjectSummary, Hunter Oaks, Endovascular

    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
     трябва
    -0.07
     aufgrund
    -0.06
     kutoka
    -0.06
     Australien
    -0.06
     शेवट
    -0.06
     debido
    -0.06
     from
    -0.06
     cierto
    -0.06
    argent
    -0.06
     bergantung
    -0.06
    POSITIVE LOGITS
     not
    0.07
    RELATED
    0.06
    ↵
    0.06
    Simply
    0.06
    ೊಂದಿಗೆ
    0.06
     tional
    0.06
    并
    0.06
    ི
    0.06
     ensuring
    0.06
     הת
    0.06
    Activations Density 0.002%

    No Known Activations