© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120631
    Prev
    Next
    INDEX
    Explanations

    professions and their associated words

    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
     მნიშვნელ
    -0.06
     সর্বপ্রথম
    -0.06
     paddling
    -0.06
     obliter
    -0.06
    이를
    -0.06
     নির্মম
    -0.06
     સંપૂર્ણ
    -0.05
     semelhantes
    -0.05
     absol
    -0.05
     wichtiger
    -0.05
    POSITIVE LOGITS
     they
    0.10
     our
    0.10
     наших
    0.09
     nossos
    0.09
     они
    0.09
     нашего
    0.08
     нашем
    0.08
     ہمارے
    0.08
     each
    0.08
    是我们
    0.08
    Activations Density 0.030%

    No Known Activations