© 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. 117003
    Prev
    Next
    INDEX
    Explanations

    metastasis prevention

    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
     Lyrics
    -0.06
    user
    -0.06
    食用
    -0.06
    Consume
    -0.05
     Radi
    -0.05
    Have
    -0.05
     Menn
    -0.05
    Kr
    -0.05
     surrounding
    -0.05
     Annu
    -0.05
    POSITIVE LOGITS
     prevention
    0.07
    预防
    0.07
     preventative
    0.07
     courier
    0.07
     precautionary
    0.07
     교통
    0.06
     investment
    0.06
     foresight
    0.06
     jurisdictional
    0.06
     prevenir
    0.06
    Activations Density 0.012%

    No Known Activations