© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129396
    Prev
    Next
    INDEX
    Explanations

    experimental spike

    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
     vertigo
    -0.06
     claust
    -0.06
     fresher
    -0.06
    joint
    -0.06
     egress
    -0.06
    строи
    -0.06
    ৈধ
    -0.06
     новая
    -0.05
     neue
    -0.05
     обновление
    -0.05
    POSITIVE LOGITS
    สำหรับการ
    0.07
     lashes
    0.07
     사용
    0.06
     stallions
    0.06
     використовувати
    0.06
     قوة
    0.06
    搭配
    0.06
     використання
    0.06
     Verwendung
    0.06
    組合
    0.06
    Activations Density 0.002%

    No Known Activations