© 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. 118086
    Prev
    Next
    INDEX
    Explanations

    medical therapy and treatment

    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
     prevention
    -0.07
    Water
    -0.06
     water
    -0.06
     protection
    -0.06
     केलं
    -0.06
     protezione
    -0.06
     অঞ্চলের
    -0.06
     prevenção
    -0.06
    Early
    -0.06
     Water
    -0.06
    POSITIVE LOGITS
     የማይ
    0.07
    проек
    0.06
     offshore
    0.06
     capacidad
    0.06
     হাজার
    0.06
     polish
    0.06
     posiblemente
    0.06
    project
    0.06
     estimado
    0.06
     perspectiva
    0.06
    Activations Density 0.031%

    No Known Activations