© 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. 119702
    Prev
    Next
    INDEX
    Explanations

    medical instructions, diet, therapy, care

    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
     sintet
    -0.06
     fand
    -0.06
    SCR
    -0.06
     വഹ
    -0.06
     anonymously
    -0.06
    scr
    -0.06
    เว
    -0.06
    landmark
    -0.06
     思う
    -0.05
     SCR
    -0.05
    POSITIVE LOGITS
     وكذلك
    0.07
    യ്ക്ക്
    0.07
     літоў
    0.07
     メガネ
    0.07
     пациента
    0.06
    认真
    0.06
     patient
    0.06
     valamint
    0.06
     hänen
    0.06
    horas
    0.06
    Activations Density 0.011%

    No Known Activations