© 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. 117918
    Prev
    Next
    INDEX
    Explanations

    arrhythmia and tachycardia

    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
     classic
    -0.06
     musica
    -0.06
    classic
    -0.06
     one
    -0.06
    硬件
    -0.06
     eight
    -0.06
     genuinely
    -0.06
    baixo
    -0.06
     assertive
    -0.06
     ছেলেরা
    -0.06
    POSITIVE LOGITS
    எ
    0.07
     ιδ
    0.06
     tenements
    0.06
     zvlá
    0.06
     במהלך
    0.06
     dolom
    0.06
     یون
    0.06
     averted
    0.06
     divaric
    0.05
     آور
    0.05
    Activations Density 0.011%

    No Known Activations