© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118296
    Prev
    Next
    INDEX
    Explanations

    code or function delimiters

    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
    ?
    -0.07
    the
    -0.06
    table
    -0.06
    anything
    -0.06
     stumbled
    -0.06
     निशुल्क
    -0.06
     энцикло
    -0.05
     fathom
    -0.05
     ஸ்ப
    -0.05
    냐
    -0.05
    POSITIVE LOGITS
    仍然
    0.07
     bedeut
    0.07
     cinque
    0.06
    很少
    0.06
     vẫn
    0.06
     Anschließend
    0.06
     اقدامات
    0.06
    ابقة
    0.06
    进行
    0.06
     उनके
    0.06
    Activations Density 0.003%

    No Known Activations