© 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. 117879
    Prev
    Next
    INDEX
    Explanations

    medical, technical, and programming terms

    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
    ⾃
    -0.06
    แม้
    -0.06
     mezz
    -0.06
     рекомен
    -0.06
     recommended
    -0.06
     justru
    -0.06
    recommended
    -0.06
     ਅਤੇ
    -0.06
     எந்த
    -0.05
     நூற்ற
    -0.05
    POSITIVE LOGITS
    such
    0.08
     such
    0.06
     ceas
    0.06
     effort
    0.06
     forthcoming
    0.06
     herbicide
    0.06
    effort
    0.06
     сила
    0.06
     câmera
    0.06
     constantly
    0.05
    Activations Density 0.002%

    No Known Activations