© 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. 118182
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and units

    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
    however
    -0.07
     darf
    -0.07
    每個
    -0.07
     each
    -0.07
     however
    -0.07
    Each
    -0.06
     może
    -0.06
    每个
    -0.06
     tiap
    -0.06
     karena
    -0.06
    POSITIVE LOGITS
     культура
    0.06
     subdivisions
    0.06
     Honor
    0.06
    ประเทศ
    0.06
     roupas
    0.06
     shrink
    0.05
     одежда
    0.05
     ऑपरेटिंग
    0.05
     zindagi
    0.05
     privada
    0.05
    Activations Density 0.004%

    No Known Activations