© 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. 129540
    Prev
    Next
    INDEX
    Explanations

    administration and support staff

    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
     പുതിയ
    -0.06
     neuen
    -0.06
     yeni
    -0.06
     new
    -0.06
     ہونے
    -0.06
    صبحت
    -0.06
     दोस्तों
    -0.06
    झन
    -0.06
     νέ
    -0.06
     جانے
    -0.06
    POSITIVE LOGITS
    必需
    0.07
     administration
    0.06
     administratif
    0.06
     служби
    0.06
     Administration
    0.06
    papier
    0.06
     într
    0.06
     approach
    0.06
     Family
    0.06
     प्रशासनिक
    0.06
    Activations Density 0.010%

    No Known Activations