© 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. 118908
    Prev
    Next
    INDEX
    Explanations

    combinations, permutations, or possible sequences

    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
    성이
    -0.07
    を選
    -0.07
     выбра
    -0.06
    选
    -0.06
     selecting
    -0.06
     chosen
    -0.06
    תוך
    -0.06
     выбор
    -0.06
     selected
    -0.06
    幸运
    -0.06
    POSITIVE LOGITS
     fácilmente
    0.06
     isso
    0.06
    FI
    0.06
     শিশ
    0.06
     इस्तेमाल
    0.06
     utilizzati
    0.06
     wcześniej
    0.05
    主管部门
    0.05
     업무
    0.05
     schnell
    0.05
    Activations Density 0.008%

    No Known Activations