© 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. 116089
    Prev
    Next
    INDEX
    Explanations

    Spanish league president Javier Tebas

    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
    步骤
    -0.07
    步驟
    -0.07
     และ
    -0.07
     colegio
    -0.06
     коюм
    -0.06
    应用的
    -0.06
     进行
    -0.06
     Few
    -0.06
     коюмдар
    -0.06
     发表
    -0.06
    POSITIVE LOGITS
     spying
    0.05
    ান্
    0.05
    光
    0.05
     ohmic
    0.05
     우리는
    0.05
    hz
    0.05
     «
    0.05
    ;
    0.05
     Kyrie
    0.05
    בי
    0.05
    Activations Density 0.001%

    No Known Activations