© 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. 117652
    Prev
    Next
    INDEX
    Explanations

    medical specialty procedures and technical terms

    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
     Avenue
    -0.06
     v
    -0.06
     bungalows
    -0.06
     transformative
    -0.06
    ૃત
    -0.06
     retirement
    -0.06
    assian
    -0.06
    斜
    -0.05
     northbound
    -0.05
     pembangunan
    -0.05
    POSITIVE LOGITS
    储存
    0.07
     Lösung
    0.07
     شاف
    0.06
     ahora
    0.06
     постра
    0.06
     ಬಾರಿ
    0.06
     solução
    0.06
     సమావేశ
    0.06
     soluzione
    0.06
     caged
    0.06
    Activations Density 0.011%

    No Known Activations