© 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. 119217
    Prev
    Next
    INDEX
    Explanations

    action, conflict, and character roles

    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
    、
    -0.06
     ማ
    -0.06
    一个
    -0.06
    কোন
    -0.06
    上的
    -0.06
    Any
    -0.06
     dowol
    -0.06
     Jorge
    -0.06
    小
    -0.05
     Any
    -0.05
    POSITIVE LOGITS
     ಅನೇಕ
    0.07
    毎回
    0.07
    每月
    0.07
     mainten
    0.07
     victories
    0.07
    每次
    0.07
     然後
    0.07
    每年
    0.06
     بسیاری
    0.06
     первые
    0.06
    Activations Density 0.009%

    No Known Activations