© 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. 129653
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and foreign words

    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
     change
    -0.06
    改变
    -0.06
    部分
    -0.06
     измене
    -0.06
     zmian
    -0.06
     changes
    -0.06
     Done
    -0.06
    เปลี่ยนแปลง
    -0.06
     changed
    -0.06
     Regarding
    -0.05
    POSITIVE LOGITS
     trotz
    0.07
    Meanwhile
    0.07
    Despite
    0.07
    nearest
    0.06
     ყველ
    0.06
     nearest
    0.06
     আদাল
    0.06
     sống
    0.06
     cercana
    0.06
    despite
    0.06
    Activations Density 0.007%

    No Known Activations