© 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. 118240
    Prev
    Next
    INDEX
    Explanations

    lung 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
    面临
    -0.07
    ˌ
    -0.06
    失败
    -0.06
    力和
    -0.06
     since
    -0.06
     honest
    -0.06
    度和
    -0.05
    និង
    -0.05
     width
    -0.05
     て
    -0.05
    POSITIVE LOGITS
     চিন
    0.07
    uming
    0.06
     осві
    0.06
     incul
    0.06
     ilumin
    0.06
     ebenfalls
    0.06
     പ്രത്യേ
    0.06
     vins
    0.06
     inteligente
    0.06
     education
    0.06
    Activations Density 0.011%

    No Known Activations