© 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. 120208
    Prev
    Next
    INDEX
    Explanations

    they/them/combined/plural

    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
     agricoles
    -0.06
    দিষ্ট
    -0.06
     quoique
    -0.06
     požad
    -0.06
    Notwithstanding
    -0.06
     dość
    -0.06
     लेवल
    -0.06
    בל
    -0.06
     kategori
    -0.06
    跑到
    -0.06
    POSITIVE LOGITS
     mereka
    0.08
     BOTH
    0.07
    combined
    0.06
    original
    0.06
     combined
    0.06
    他们
    0.06
     combining
    0.06
    他們
    0.06
     veel
    0.06
     they
    0.06
    Activations Density 0.001%

    No Known Activations