© 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. 118995
    Prev
    Next
    INDEX
    Explanations

    medical and economic terms

    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
     despite
    -0.07
    despite
    -0.06
     ब्रांच
    -0.06
     दोन
    -0.06
     trotz
    -0.06
     특히
    -0.06
     মন্দ
    -0.06
    )$-
    -0.06
     ভারতের
    -0.06
     رغم
    -0.06
    POSITIVE LOGITS
     :\
    0.07
     :"
    0.07
     Ambassadors
    0.07
     específicas
    0.06
     всей
    0.06
     أنها
    0.06
     ""
    0.06
     “”
    0.06
     sdf
    0.06
     જુ
    0.06
    Activations Density 0.055%

    No Known Activations