© 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. 129224
    Prev
    Next
    INDEX
    Explanations

    grades examples problem

    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
     کھیلیں
    -0.07
     крити
    -0.06
     pedagog
    -0.06
    learning
    -0.06
     critiques
    -0.06
     تعلیم
    -0.06
    राजस्थान
    -0.06
     Curriculum
    -0.06
     교육
    -0.06
    ដ្ឋ
    -0.06
    POSITIVE LOGITS
     হইতেই
    0.07
     skyscraper
    0.06
     برای
    0.06
     circumstance
    0.06
     கேட்க
    0.06
     untuk
    0.06
     stretchy
    0.06
     навіть
    0.06
    作成
    0.06
     для
    0.06
    Activations Density 0.001%

    No Known Activations