© 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. 117397
    Prev
    Next
    INDEX
    Explanations

    introduction to

    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
     anderer
    -0.07
     Vázquez
    -0.06
     sediment
    -0.06
     parser
    -0.06
     Sanskrit
    -0.06
    parser
    -0.06
     Š
    -0.06
    JAN
    -0.06
    റിൽ
    -0.06
     sparsely
    -0.06
    POSITIVE LOGITS
     if
    0.07
    如果有
    0.06
     each
    0.06
    若
    0.06
    如果我们
    0.06
     ________
    0.06
     चाहें
    0.06
     ___
    0.06
     запрос
    0.06
    *:
    0.06
    Activations Density 0.022%

    No Known Activations