© 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. 116715
    Prev
    Next
    INDEX
    Explanations

    layout_ or Savings Account or Q:

    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
    対象
    -0.07
     anunció
    -0.06
     доступ
    -0.06
     são
    -0.06
     대상
    -0.06
     einsch
    -0.06
     news
    -0.06
    Номер
    -0.06
     coveted
    -0.06
     groundbreaking
    -0.06
    POSITIVE LOGITS
     rejects
    0.06
     rejection
    0.06
     rejected
    0.06
     rejecting
    0.06
     সেটা
    0.06
    wr
    0.05
    ㅋㅋㅋㅋ
    0.05
    差点
    0.05
     trzech
    0.05
    ㅋㅋㅋ
    0.05
    Activations Density 0.001%

    No Known Activations