© 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. 130515
    Prev
    Next
    INDEX
    Explanations

    words/phrases indicating time or reporting speech

    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
     efforts
    -0.08
     RNG
    -0.07
     analyzes
    -0.06
    alá
    -0.06
     analysis
    -0.06
     Efforts
    -0.06
     বাবুর
    -0.06
     comparisons
    -0.06
    地球
    -0.05
     تلاش
    -0.05
    POSITIVE LOGITS
     usually
    0.08
     mindig
    0.07
     manchmal
    0.07
     Sometimes
    0.07
    Usually
    0.07
     Usually
    0.07
     обычно
    0.07
    電話
    0.07
    Sometimes
    0.07
     जेव्हा
    0.07
    Activations Density 0.068%

    No Known Activations