© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130750
    Prev
    Next
    INDEX
    Explanations

    McLeod from, Brian Duerden

    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
     Ferrari
    -0.06
     to
    -0.06
     Data
    -0.06
    优质
    -0.06
    cpuCycle
    -0.06
     frustrating
    -0.06
    量子
    -0.06
    Winter
    -0.06
    λευ
    -0.06
     Carlsbad
    -0.06
    POSITIVE LOGITS
     сельского
    0.07
     unst
    0.06
    ucked
    0.06
     첫
    0.06
     дерев
    0.06
     laborers
    0.06
     homegrown
    0.06
     সংবাদ
    0.06
     बाकी
    0.06
     обору
    0.06
    Activations Density 0.007%

    No Known Activations