© 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. 118275
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    XXXX
    -0.05
     All
    -0.05
     however
    -0.05
     Even
    -0.05
     XX
    -0.05
     Ongoing
    -0.05
    ori
    -0.05
     allerdings
    -0.05
     However
    -0.05
     regularly
    -0.05
    POSITIVE LOGITS
     mereka
    0.07
     یا
    0.07
    意味
    0.06
    ীয়তে
    0.06
     הם
    0.06
     Preise
    0.06
     ඔවුන්
    0.06
     उन्हें
    0.06
     அல்லது
    0.06
     ihnen
    0.06
    Activations Density 0.025%

    No Known Activations