© 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. 129969
    Prev
    Next
    INDEX
    Explanations

    cryptographic operations and specifications

    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
     silah
    -0.06
     confidential
    -0.06
    exécution
    -0.06
     Degrad
    -0.06
     উভয়
    -0.06
     поговорим
    -0.06
     Confidential
    -0.06
     technique
    -0.06
     weapons
    -0.06
    DataBase
    -0.06
    POSITIVE LOGITS
     différents
    0.06
     प्रतिनिधियों
    0.06
     farklı
    0.06
     PO
    0.06
    Nobody
    0.06
    漉
    0.05
     فاتت
    0.05
    だったら
    0.05
     smaller
    0.05
    క్క
    0.05
    Activations Density 0.007%

    No Known Activations