© 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. 129952
    Prev
    Next
    INDEX
    Explanations

    neurological complications and disease

    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
    increases
    -0.06
    increased
    -0.06
    ALTERN
    -0.06
    霈
    -0.06
     regardless
    -0.06
     обосно
    -0.06
     despite
    -0.06
     increases
    -0.06
     increase
    -0.06
     dynamique
    -0.05
    POSITIVE LOGITS
     reading
    0.07
     लष्
    0.07
     читать
    0.07
     wandered
    0.06
     स्कूल
    0.06
    ológico
    0.06
     squint
    0.06
     शुरुआती
    0.06
    しか
    0.06
    学校
    0.06
    Activations Density 0.062%

    No Known Activations