© 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. 120192
    Prev
    Next
    INDEX
    Explanations

    ketoacidosis, rhabdomyolysis

    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
     Servo
    -0.06
     delicate
    -0.06
     নৃশংস
    -0.06
     മികച്ച
    -0.06
     servo
    -0.06
     değerli
    -0.06
    无关
    -0.06
     हानिकारक
    -0.06
    ครับ
    -0.06
    難しい
    -0.06
    POSITIVE LOGITS
     सरी
    0.07
     ketones
    0.07
     formazione
    0.06
     excitation
    0.06
     penyimpanan
    0.06
    极端
    0.06
     formation
    0.06
     addictions
    0.06
     काय
    0.06
     excited
    0.05
    Activations Density 0.006%

    No Known Activations