© 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. 116214
    Prev
    Next
    INDEX
    Explanations

    retrospective, enucleation, lymphoma, dryer

    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
    今の
    -0.06
     now
    -0.06
     읽
    -0.06
     ಸೇವ
    -0.06
    今日の
    -0.06
    今日
    -0.06
     without
    -0.06
    读
    -0.06
     привы
    -0.05
     чувстви
    -0.05
    POSITIVE LOGITS
     उसका
    0.06
     Dryer
    0.06
     когато
    0.06
     laundry
    0.06
     dryer
    0.06
     bruge
    0.06
     lymphoma
    0.06
     বাগ
    0.06
     रौनक
    0.06
    楽しい
    0.06
    Activations Density 0.056%

    No Known Activations