© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120940
    Prev
    Next
    INDEX
    Explanations

    punished

    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
    Negative Logits
    与其他
    -0.07
    inan
    -0.06
     यस
    -0.06
     esses
    -0.06
    还会
    -0.06
     ইঙ্গিত
    -0.06
    бую
    -0.06
    вые
    -0.05
     перед
    -0.05
    に関して
    -0.05
    POSITIVE LOGITS
     конвер
    0.06
     थांब
    0.06
    airplane
    0.06
    逛
    0.06
     名称
    0.06
    叫做
    0.06
     "("
    0.06
     название
    0.06
     দুর্ভিক্ষ
    0.06
     more
    0.06
    Activations Density 0.041%

    No Known Activations