© 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. 115910
    Prev
    Next
    INDEX
    Explanations

    club or chapter names

    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
    作る
    -0.07
     सही
    -0.06
     cafe
    -0.06
    事で
    -0.06
    віта
    -0.06
    商家
    -0.06
    ☕
    -0.06
     grassroots
    -0.06
     बोर्ड
    -0.06
     youth
    -0.06
    POSITIVE LOGITS
    次数
    0.06
    大型
    0.06
    ครั้ง
    0.06
     thrice
    0.05
     breathtaking
    0.05
     expertise
    0.05
     prohibition
    0.05
    Sampling
    0.05
    qq
    0.05
     प्रकारचे
    0.05
    Activations Density 0.028%

    No Known Activations