© 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. 118340
    Prev
    Next
    INDEX
    Explanations

    usually, typically, important

    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
    मित्र
    -0.06
     bipart
    -0.06
     workable
    -0.06
     ऑपरेट
    -0.05
     pony
    -0.05
     স্বতন্ত্র
    -0.05
     dashboard
    -0.05
     এপ্রিল
    -0.05
     କ
    -0.05
     कठिन
    -0.05
    POSITIVE LOGITS
     Usually
    0.07
    usually
    0.07
    Usually
    0.07
     biasanya
    0.06
    typically
    0.06
     কূট
    0.06
     usually
    0.06
     Biasanya
    0.06
    應該
    0.06
     wichtige
    0.06
    Activations Density 0.013%

    No Known Activations