© 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. 130329
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     phone
    -0.06
    XSSF
    -0.06
    phone
    -0.06
     Phone
    -0.06
     telephone
    -0.06
     মাই
    -0.06
     estimates
    -0.06
     ESTIM
    -0.05
     consultation
    -0.05
     miejscowości
    -0.05
    POSITIVE LOGITS
    最後に
    0.07
    ṟ
    0.07
     রেখেছে
    0.07
     vrát
    0.06
    アプリ
    0.06
     cuối
    0.06
     τελευτα
    0.06
     build
    0.06
     dismantle
    0.06
     retorna
    0.06
    Activations Density 0.030%

    No Known Activations