© 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. 117655
    Prev
    Next
    INDEX
    Explanations

    medical prefixes

    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
    स्फी
    -0.06
    ￳
    -0.06
    തിനാൽ
    -0.06
     mémoire
    -0.06
     अधिक
    -0.06
     Memory
    -0.06
    NAC
    -0.06
     جميع
    -0.06
    するので
    -0.06
     fara
    -0.06
    POSITIVE LOGITS
     idealized
    0.06
     summarized
    0.06
     desirous
    0.06
    降り
    0.06
    ↵
    0.06
    িলার
    0.06
     summarised
    0.06
     entfernt
    0.05
     kindly
    0.05
     grasped
    0.05
    Activations Density 0.022%

    No Known Activations