© 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. 120131
    Prev
    Next
    INDEX
    Explanations

    range of years

    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
     --------
    -0.06
    assert
    -0.06
     =====
    -0.06
    相關
    -0.06
     ----
    -0.06
     /,
    -0.06
     امور
    -0.06
     constitu
    -0.06
     And
    -0.06
     различных
    -0.06
    POSITIVE LOGITS
     this
    0.08
     этому
    0.07
     لهذه
    0.07
    utan
    0.06
     этом
    0.06
    这种
    0.06
     этой
    0.06
    のような
    0.06
    這種
    0.06
    哪個
    0.06
    Activations Density 0.002%

    No Known Activations