© 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. 128454
    Prev
    Next
    INDEX
    Explanations

    experimental setup apparatus

    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
    近年
    -0.07
     without
    -0.07
    without
    -0.07
    近年来
    -0.07
    最近
    -0.06
     지금까지
    -0.06
    已被
    -0.06
    还可以
    -0.06
    움을
    -0.06
    可通过
    -0.06
    POSITIVE LOGITS
     envisioned
    0.07
     intend
    0.06
     basiert
    0.06
    |\
    0.06
     अगला
    0.06
     দাড়
    0.06
     agreed
    0.06
     the
    0.06
    ယ့်
    0.06
    更多
    0.06
    Activations Density 0.002%

    No Known Activations