© 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. 120288
    Prev
    Next
    INDEX
    Explanations

    medical conditions or treatments

    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
     velocity
    -0.06
     revol
    -0.06
     walkers
    -0.06
    civil
    -0.05
    velocity
    -0.05
     symmetry
    -0.05
    心里
    -0.05
    無理
    -0.05
    motor
    -0.05
     passing
    -0.05
    POSITIVE LOGITS
     হয়তো
    0.06
    確かに
    0.06
     MNC
    0.06
     Mekong
    0.06
    ociaż
    0.06
    皮膚
    0.06
     நீண்ட
    0.06
     longterm
    0.06
     débar
    0.06
     emigrated
    0.06
    Activations Density 0.084%

    No Known Activations