© 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. 117880
    Prev
    Next
    INDEX
    Explanations

    gastric cancer

    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
     ATV
    -0.07
    apeut
    -0.07
     steroid
    -0.07
     ultraviolet
    -0.06
     Oxfordshire
    -0.06
     astronom
    -0.06
    沇
    -0.06
    等等
    -0.06
     véhicules
    -0.06
    umably
    -0.06
    POSITIVE LOGITS
     කු
    0.06
    役に
    0.06
     yemek
    0.06
     morts
    0.06
     heartily
    0.06
     Matsuda
    0.06
     shipbuilding
    0.06
     Polskiej
    0.06
     внеш
    0.06
     япон
    0.06
    Activations Density 0.020%

    No Known Activations